Programming artificial intelligence to make fairness assessments of texts through top-down rules, bottom-up training, or hybrid approaches, has presented the challenge of defining cross-cultural fairness. In this paper a simple method is presented which uses vectors to discover if a verb is unfair or fair. It uses already existing relational social ontologies inherent in Word Embeddings and thus requires no training. The plausibility of the approach rests on two premises. That individuals consider fair acts those that they would (...) be willing to accept if done to themselves. Secondly, that such a construal is ontologically reflected in Word Embeddings, by virtue of their ability to reflect the dimensions of such a perception. These dimensions being: responsibility vs. irresponsibility, gain vs. loss, reward vs. sanction, joy vs. pain, all as a single vector. The paper finds it possible to quantify and qualify a verb as fair or unfair by calculating the cosine similarity of the said verb’s embedding vector against FairVec—which represents the above dimensions. We apply this to Glove and Word2Vec embeddings. Testing on a list of verbs produces an F1 score of 95.7, which is improved to 97.0. Lastly, a demonstration of the method’s applicability to sentence measurement is carried out. (shrink)

Programming artificial intelligence to make fairness assessments of texts through top-down rules, bottom-up training, or hybrid approaches, has presented the challenge of defining cross-cultural fairness. In this paper a simple method is presented which uses vectors to discover if a verb is unfair or fair. It uses already existing relational social ontologies inherent in Word Embeddings and thus requires no training. The plausibility of the approach rests on two premises. That individuals consider fair acts those that they would (...) be willing to accept if done to themselves. Secondly, that such a construal is ontologically reflected in Word Embeddings, by virtue of their ability to reflect the dimensions of such a perception. These dimensions being: responsibility vs. irresponsibility, gain vs. loss, reward vs. sanction, joy vs. pain, all as a single vector. The paper finds it possible to quantify and qualify a verb as fair or unfair by calculating the cosine similarity of the said verb’s embedding vector against FairVec—which represents the above dimensions. We apply this to Glove and Word2Vec embeddings. Testing on a list of verbs produces an F1 score of 95.7, which is improved to 97.0. Lastly, a demonstration of the method’s applicability to sentence measurement is carried out. (shrink)

Lexical ambiguity—the phenomenon of a single word having multiple, distinguishable senses—is pervasive in language. Both the degree of ambiguity of a word (roughly, its number of senses) and the relatedness of those senses have been found to have widespread effects on language acquisition and processing. Recently, distributional approaches to semantics, in which a word's meaning is determined by its contexts, have led to successful research quantifying the degree of ambiguity, but these measures have not distinguished between the (...) ambiguity of words with multiple related senses versus multiple unrelated meanings. In this work, we present the first assessment of whether distributional meaning representations can capture the ambiguity structure of a word, including both the number and relatedness of senses. On a very large sample of English words, we find that some, but not all, distributional semantic representations that we test exhibit detectable differences between sets of monosemes (unambiguous words; N = 964), polysemes (with multiple related senses; N = 4,096), and homonyms (with multiple unrelated senses; N = 355). Our findings begin to answer open questions from earlier work regarding whether distributional semantic representations of words, which successfully capture various semantic relationships, also reflect fine‐grained aspects of meaning structure that influence human behavior. Our findings emphasize the importance of measuring whether proposed lexical representations capture such distinctions: In addition to standard benchmarks that test the similarity structure of distributional semantic models, we need to also consider whether they have cognitively plausible ambiguity structure. (shrink)

The pervasive use of distributional semantic models or word embeddings for both cognitive modeling and practical application is because of their remarkable ability to represent the meanings of words. However, relatively little effort has been made to explore what types of information are encoded in distributional word vectors. Knowing the internal knowledge embedded in word vectors is important for cognitive modeling using distributional semantic models. Therefore, in this paper, we attempt to identify the knowledge encoded (...) in word vectors by conducting a computational experiment using Binder et al.'s (2016) featural conceptual representations based on neurobiologically motivated attributes. In an experiment, these conceptual vectors are predicted from text‐based word vectors using a neural network and linear transformation, and prediction performance is compared among various types of information. The analysis demonstrates that abstract information is generally predicted more accurately by word vectors than perceptual and spatiotemporal information, and specifically, the prediction accuracy of cognitive and social information is higher. Emotional information is also found to be successfully predicted for abstract words. These results indicate that language can be a major source of knowledge about abstract attributes, and they support the recent view that emphasizes the importance of language for abstract concepts. Furthermore, we show that word vectors can capture some types of perceptual and spatiotemporal information about concrete concepts and some relevant word categories. This suggests that language statistics can encode more perceptual knowledge than often expected. (shrink)

Regular polysemes are sets of ambiguous words that all share the same relationship between their meanings, such as CHICKEN and LOBSTER both referring to an animal or its meat. To probe how a distributional semantic model, here exemplified by bidirectional encoder representations from transformers (BERT), represents regular polysemy, we analyzed whether its embeddings support answering sense analogy questions similar to “is the mapping between CHICKEN (as an animal) and CHICKEN (as a meat) similar to that which maps between LOBSTER (as (...) an animal) to LOBSTER (as a meat)?” We did so using the LRcos model, which combines a logistic regression classifier of different categories (e.g., animal vs. meat) with a measure of cosine similarity. We found that (a) the model was sensitive to the shared structure within a given regular relationship; (b) the shared structure varies across different regular relationships (e.g., animal/meat vs. location/organization), potentially reflective of a “regularity continuum;” (c) some high-order latent structure is shared across different regular relationships, suggestive of a similar latent structure across different types of relationships; and (d) there is a lack of evidence for the aforementioned effects being explained by meaning overlap. Lastly, we found that both components of the LRcos model made important contributions to accurate responding and that a variation of this method could yield an accuracy boost of 10% in answering sense analogy questions. These findings enrich previous theoretical work on regular polysemy with a computationally explicit theory and methods, and provide evidence for an important organizational principle for the mental lexicon and the broader conceptual knowledge system. (shrink)

Most, if not all, philosophers agree that computers cannot learn what words refers to from raw text alone. While many attacked Searle’s Chinese Room thought experiment, no one seemed to question this most basic assumption. For how can computers learn something that is not in the data? Emily Bender and Alexander Koller ( 2020 ) recently presented a related thought experiment—the so-called Octopus thought experiment, which replaces the rule-based interlocutor of Searle’s thought experiment with a neural language model. The Octopus (...) thought experiment was awarded a best paper prize and was widely debated in the AI community. Again, however, even its fiercest opponents accepted the premise that what a word refers to cannot be induced in the absence of direct supervision. I will argue that what a word refers to _is_ probably learnable from raw text alone. Here’s why: higher-order concept co-occurrence statistics are stable across languages and across modalities, because language use (universally) reflects the world we live in (which is relatively stable). Such statistics are sufficient to establish what words refer to. My conjecture is supported by a literature survey, a thought experiment, and an actual experiment. (shrink)

Vector models of language are based on the contextual aspects of language, the distributions of words and how they co-occur in text. Truth conditional models focus on the logical aspects of language, compositional properties of words and how they compose to form sentences. In the truth conditional approach, the denotation of a sentence determines its truth conditions, which can be taken to be a truth value, a set of possible worlds, a context change potential, or similar. In the vector models, (...) the degree of co-occurrence of words in context determines how similar the meanings of words are. In this paper, we put these two models together and develop a vector semantics for language based on the simply typed lambda calculus models of natural language. We provide two types of vector semantics: a static one that uses techniques familiar from the truth conditional tradition and a dynamic one based on a form of dynamic interpretation inspired by Heim’s context change potentials. We show how the dynamic model can be applied to entailment between a corpus and a sentence and provide examples. (shrink)

We develop a vector space semantics for verb phrase ellipsis with anaphora using type-driven compositional distributional semantics based on the Lambek calculus with limited contraction of Jäger. Distributional semantics has a lot to say about the statistical collocation based meanings of content words, but provides little guidance on how to treat function words. Formal semantics on the other hand, has powerful mechanisms for dealing with relative pronouns, coordinators, and the like. Type-driven compositional distributional semantics brings these two models together. We (...) review previous compositional distributional models of relative pronouns, coordination and a restricted account of ellipsis in the DisCoCat framework of Coecke et al. :1079–1100, 2013). We show how DisCoCat cannot deal with general forms of ellipsis, which rely on copying of information, and develop a novel way of connecting typelogical grammar to distributional semantics by assigning vector interpretable lambda terms to derivations of LCC in the style of Muskens and Sadrzadeh Logical aspects of computational linguistics, Springer, Berlin, 2016). What follows is an account of ellipsis in which word meanings can be copied: the meaning of a sentence is now a program with non-linear access to individual word embeddings. We present the theoretical setting, work out examples, and demonstrate our results with a state of the art distributional model on an extended verb disambiguation dataset. (shrink)

The Distributional Compositional Categorical model is a mathematical framework that provides compositional semantics for meanings of natural language sentences. It consists of a computational procedure for constructing meanings of sentences, given their grammatical structure in terms of compositional type-logic, and given the empirically derived meanings of their words. For the particular case that the meaning of words is modelled within a distributional vector space model, its experimental predictions, derived from real large scale data, have outperformed other empirically validated methods that (...) could build vectors for a full sentence. This success can be attributed to a conceptually motivated mathematical underpinning, something which the other methods lack, by integrating qualitative compositional type-logic and quantitative modelling of meaning within a category-theoretic mathematical framework. The type-logic used in the DisCoCat model is Lambekʼs pregroup grammar. Pregroup types form a posetal compact closed category, which can be passed, in a functorial manner, on to the compact closed structure of vector spaces, linear maps and tensor product. The diagrammatic versions of the equational reasoning in compact closed categories can be interpreted as the flow of word meanings within sentences. Pregroups simplify Lambekʼs previous type-logic, the Lambek calculus. The latter and its extensions have been extensively used to formalise and reason about various linguistic phenomena. Hence, the apparent reliance of the DisCoCat on pregroups has been seen as a shortcoming. This paper addresses this concern, by pointing out that one may as well realise a functorial passage from the original type-logic of Lambek, a monoidal bi-closed category, to vector spaces, or to any other model of meaning organised within a monoidal bi-closed category. The corresponding string diagram calculus, due to Baez and Stay, now depicts the flow of word meanings, and also reflects the structure of the parse trees of the Lambek calculus. (shrink)

This article describes the use of continuous vector space models for reasoning with a formal knowledge base. The practical significance of these models is that they support fast, approximate but robust inference and hypothesis generation, which is complementary to the slow, exact, but sometimes brittle behaviour of more traditional deduction engines such as theorem provers.The article explains the way logical connectives can be used in semantic vector models, and summarizes the development of Predication-based Semantic Indexing, which involves the use of (...) Vector Symbolic Architectures to represent the concepts and relationships from a knowledge base of subject-predicate-object triples. Experiments show that the use of continuous models for formal reasoning is not only possible, but already demonstrably effective for some recognized informatics tasks, and showing promise in other traditional problem areas. Examples described in this article include: predicting new uses for existing drugs in biomedical informatics; removing unwanted meanings from search results in information retrieval and concept navigation; type inference from attributes; comparing words based on their orthography; and representing tabular data, including modelling numerical values.The algorithms and techniques described in this article are all publicly released and freely available in the Semantic Vectors open-source software package.1. (shrink)

Vector models of language are based on the contextual aspects of words and how they co-occur in text. Truth conditional models focus on the logical aspects of language, the denotations of phrases, and their compositional properties. In the latter approach the denotation of a sentence determines its truth conditions and can be taken to be a truth value, a set of possible worlds, a context change potential, or similar. In this short paper, we develop a vector semantics for language based (...) on the simply typed lambda calculus. Our semantics uses techniques familiar from the truth conditional tradition and is based on a form of dynamic interpretation inspired by Heim's context updates. (shrink)

From Curriculum Vitae parsing to web search and recommendation systems, Word2Vec and other word embedding techniques have an increasing presence in everyday interactions in human society. Biases, such as gender bias, have been thoroughly researched and evidenced to be present in word embeddings. Most of the research focuses on discovering and mitigating gender bias within the frames of the vector space itself. Nevertheless, whose bias is reflected in word embeddings has not yet been investigated. Besides discovering and (...) mitigating gender bias, it is also important to examine whether a feminine or a masculine-centric view is represented in the biases of word embeddings. This way, we will not only gain more insight into the origins of the before mentioned biases, but also present a novel approach to investigating biases in Natural Language Processing systems. Based on previous research in the social sciences and gender studies, we hypothesize that masculine-centric, otherwise known as androcentric, biases are dominant in word embeddings. To test this hypothesis we used the largest English word association test data set publicly available. We compare the distance of the responses of male and female participants to cue words in a word embedding vector space. We found that the word embedding is biased towards a masculine-centric viewpoint, predominantly reflecting the worldviews of the male participants in the word association test data set. Therefore, by conducting this research, we aimed to unravel another layer of bias to be considered when examining fairness in algorithms. (shrink)

The scientific and practical fields—especially high-performance sports—increasingly request a stronger focus be placed on individual athletes in human movement science research. Machine learning methods have shown efficacy in this context by identifying the unique movement patterns of individuals and distinguishing their intra-individual changes over time. The objective of this investigation is to analyze biomechanically described movement patterns during the fatigue-related accumulation process within a single training session of a high number of repeated executions of a ballistic sports movement—specifically, the frontal (...) foot kick (mae-geri) in karate—in expert athletes. The two leading research questions presented for consideration are (1) Can characteristics of individual movement patterns be observed throughout the entire training session despite continuous changes, i.e., even as fatigue-related processes increase? and (2) How do intra-individual movement patterns change as fatigue-related processes increase throughout a training session? Sixteen expert karatekas performed 606 frontal foot kicks directed toward an imaginary target. The kicks were performed in nine sets at 80% (K-80) of the self-experienced maximal intensity. In addition, six kicks at maximal intensity (K-100) were performed after each of the nine sets. Between the sets, the participants took a 90-s break. Three-dimensional full-body kinematic data of all kicks were recorded with 10 infrared cameras. The normalized waveforms of nine upper- and lower-body joint angles were classified using a supervised machine learning method (support vector machine). The results of the classification revealed a disjunct distinction between the kinematic movement patterns of individual athletes. The identification of unique movement patterns of individual athletes was independent of the intensity and the degree of fatigue-related processes. In other words, even with the accumulation of fatigue-related processes, the unique movement patterns of an individual athlete can be clearly identified. During the training session, changes in intra-individual movement patterns could also be detected, indicating the occurrence of adaptations in individual movement patterns throughout the fatigue-related accumulation process. The results suggest that these adaptations can be modeled in terms of changes in patterns rather than increasing variance. Practical consequences are critically discussed. (shrink)

We present a longitudinal computational study on the connection between emotional and amodal word representations from a developmental perspective. In this study, children's and adult word representations were generated using the latent semantic analysis (LSA) vector space model and Word Maturity methodology. Some children's word representations were used to set a mapping function between amodal and emotional word representations with a neural network model using ratings from 9‐year‐old children. The neural network was trained and validated (...) in the child semantic space. Then, the resulting neural network was tested with adult word representations using ratings from an adult data set. Samples of 1210 and 5315 words were used in the child and the adult semantic spaces, respectively. Results suggested that the emotional valence of words can be predicted from amodal vector representations even at the child stage, and accurate emotional propagation was found in the adult word vector representations. In this way, different propagative processes were observed in the adult semantic space. These findings highlight a potential mechanism for early verbal emotional anchoring. Moreover, different multiple linear regression and mixed‐effect models revealed moderation effects for the performance of the longitudinal computational model. First, words with early maturation and subsequent semantic definition promoted emotional propagation. Second, an interaction effect between age of acquisition and abstractness was found to explain model performance. The theoretical and methodological implications are discussed. (shrink)

Over the history of research on sign languages, much scholarship has highlighted the pervasive presence of signs whose forms relate to their meaning in a non-arbitrary way. The presence of these forms suggests that sign language vocabularies are shaped, at least in part, by a pressure toward maintaining a link between form and meaning in wordforms. We use a vector space approach to test the ways this pressure might shape sign language vocabularies, examining how non-arbitrary forms are distributed within the (...) lexicons of two unrelated sign languages. Vector space models situate the representations of words in a multi-dimensional space where the distance between words indexes their relatedness in meaning. Using phonological information from the vocabularies of American Sign Language and British Sign Language, we tested whether increased similarity between the semantic representations of signs corresponds to increased phonological similarity. The results of the computational analysis showed a significant positive relationship between phonological form and semantic meaning for both sign languages, which was strongest when the sign language lexicons were organized into clusters of semantically related signs. The analysis also revealed variation in the strength of patterns across the form-meaning relationships seen between phonological parameters within each sign language, as well as between the two languages. This shows that while the connection between form and meaning is not entirely language specific, there are cross-linguistic differences in how these mappings are realized for signs in each language, suggesting that arbitrariness as well as cognitive or cultural influences may play a role in how these patterns are realized. The results of this analysis not only contribute to our understanding of the distribution of non-arbitrariness in sign language lexicons, but also demonstrate a new way that computational modeling can be harnessed in lexicon-wide investigations of sign languages. (shrink)

The use of ensemble learning, deep learning, and effective document representation methods is currently some of the most common trends to improve the overall accuracy of a text classification/categorization system. Ensemble learning is an approach to raise the overall accuracy of a classification system by utilizing multiple classifiers. Deep learning-based methods provide better results in many applications when compared with the other conventional machine learning algorithms. Word embeddings enable representation of words learned from a corpus as vectors that (...) provide a mapping of words with similar meaning to have similar representation. In this study, we use different document representations with the benefit of word embeddings and an ensemble of base classifiers for text classification. The ensemble of base classifiers includes traditional machine learning algorithms such as naïve Bayes, support vector machine, and random forest and a deep learning-based conventional network classifier. We analysed the classification accuracy of different document representations by employing an ensemble of classifiers on eight different datasets. Experimental results demonstrate that the usage of heterogeneous ensembles together with deep learning methods and word embeddings enhances the classification performance of texts. (shrink)

The number of scientific publications is growing exponentially. Research articles cite other work for various reasons and, therefore, have been studied extensively to associate documents. It is argued that not all references carry the same level of importance. It is essential to understand the reason for citation, called citation intent or function. Text information can contribute well if new natural language processing techniques are applied to capture the context of text data. In this paper, we have used contextualized word (...) embedding to find the numerical representation of text features. We further investigated the performance of various machine-learning techniques on the numerical representation of text. The performance of each of the classifiers was evaluated on two state-of-the-art datasets containing the text features. In the case of the unbalanced dataset, we observed that the linear Support Vector Machine achieved 86% accuracy for the “background” class, where the training was extensive. For the rest of the classes, including “motivation,” “extension,” and “future,” the machine was trained on less than 100 records; therefore, the accuracy was only 57 to 64%. In the case of a balanced dataset, each of the classes has the same accuracy as trained on the same size of training data. Overall, SVM performed best on both of the datasets, followed by the stochastic gradient descent classifier; therefore, SVM can produce good results as text classification on top of contextual word embedding. (shrink)

In this study, we analyzed the relationship between the amodal (semantic) development of words and two popular emotional norms (emotional valence and arousal) in English and Spanish languages. To do so, we combined the strengths of semantics from vector space models (vector length, semantic diversity, and word maturity measures), and feature-based models of emotions. First, we generated a common vector space representing the meaning of words at different developmental stages (five and four developmental stages for English and Spanish, respectively) (...) using the Word Maturity methodology to align different vector spaces. Second, we analyzed the amodal development of words through mixed-effects models with crossed random effects for words and variables using a continuous time metric. Third, the emotional norms were included as covariates in the statistical models. We evaluated more than 23,000 words, whose emotional norms were available for more than 10,000 words, in each language separately. Results showed a curve of amodal development with an increasing linear effect and a small quadratic deceleration. A relevant influence on the amodal development of words was found only for emotional valence (not for arousal), suggesting that positive words have an earlier amodal development and a less pronounced semantic change across early lifespan. (shrink)

Lexical ambiguity is pervasive in language, and the nature of the representations of an ambiguous word's multiple meanings is yet to be fully understood. With a special focus on Chinese characters, the present study first established that native speaker's perception about a character's number of meanings was heavily influenced by the availability of its distinct word formations, while whether these meanings would be perceived to be closely related was driven by further conceptual analysis. These notions were operationalized as (...) two computed metrics, which assessed the degree of dispersion across individual word formations and the degree of propinquity across clusters of word formations, respectively, in a distributional semantic space. The observed correlations between the computed and the perceived metrics indicated that the utility of word formations to tap into meaning representations of Chinese characters was indeed cognitively plausible. The results have demonstrated the extent to which distributional semantics could inform about meaning representations of Chinese characters, which has theoretical implications for the representation of ambiguous words more generally. (shrink)

With the increasing scale of e-commerce, the complexity of image content makes commodity image classification face great challenges. Image feature extraction often determines the quality of the final classification results. At present, the image feature extraction part mainly includes the underlying visual feature and the intermediate semantic feature. The intermediate semantics of the image acts as a bridge between the underlying features and the advanced semantics of the image, which can make up for the semantic gap to a certain extent (...) and has strong robustness. As a typical intermediate semantic representation method, the bag-of-visual-words model has received extensive attention in image classification. However, the traditional BoVW model loses the location information of local features, and its local feature descriptors mainly focus on the texture shape information of local regions but lack the expression of color information. Therefore, in this paper, the improved bag-of-visual-words model is presented, which contains three aspects of improvement: multiscale local region extraction; local feature description by speeded up robust features and color vector angle histogram ; and diagonal concentric rectangular pattern. Experimental results show that the three aspects of improvement to the BoVW model are complementary, while compared with the traditional BoVW and the BoVW adopting SURF + SPM, the classification accuracy of the improved BoVW is increased by 3.60% and 2.33%, respectively. (shrink)

The semantic similarity between words is one of the basic knowledge in Natural Language Processing. There have been several previous studies on measuring the similarity based on word vectors in a multi-dimensional space. In those studies, high dimensional feature vectors of words are made from words' cooccurrence in a corpus or from reference relation in a dictionary, and then the word vectors are calculated from the feature vectors through the method like principal component analysis. (...) This paper proposes a new placement method of nouns into a multi-dimensional space based on words' cooccurrence in a corpus. The proposed method doesn't use the high dimensional feature vectors of words, but is based on the idea that ``vectors corresponding to nouns which cooccur with a word w in a relation f constitute a group in the multi-dimensional space''. Although the whole meaning of nouns isn't reflected in the word vectors obtained by the pro posed method, the semantic similarity between nouns defined with the word vectors is proper for an example-based disambiguation method. (shrink)

Similarity is one of the most important relations humans perceive, arguably subserving category learning and categorization, generalization and discrimination, judgment and decision making, and other cognitive functions. Researchers have proposed a wide range of representations and metrics that could be at play in similarity judgment, yet have not comprehensively compared the power of these representations and metrics for predicting similarity within and across different semantic categories. We performed such a comparison by pairing nine prominent vector semantic representations with seven established (...) similarity metrics that could operate on these representations, as well as supervised methods for dimensional weighting in the similarity function. This approach yields a factorial model structure with 126 distinct representation‐metric pairs, which we tested on a novel dataset of similarity judgments between pairs of cohyponymic words in eight categories. We found that cosine similarity and Pearson correlation were the overall best performing unweighted similarity functions, and that word vectors derived from free association norms often outperformed word vectors derived from text (including those specialized for similarity). Importantly, models that used human similarity judgments to learn category‐specific weights on dimensions yielded substantially better predictions than all unweighted approaches across all types of similarity functions and representations, although dimension weights did not generalize well across semantic categories, suggesting strong category context effects in similarity judgment. We discuss implications of these results for cognitive modeling and natural language processing, as well as for theories of the representations and metrics involved in similarity. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:Index to Volume Fifty-SixArticlesBernier, Bernard, National Communion: Watsuji Tetsurō's Conception of Ethics, Power, and the Japanese Imperial State, 1 : 84-105Between Principle and Situation: Contrasting Styles in the Japanese and Korean Traditions of Moral Culture, Chai-sik Chung, 2 : 253-280Buxton, Nicholas, The Crow and the Coconut: Accident, Coincidence, and Causation in the Yogavāiṣṭha, 3 : 392-408Chan, Sin Yee, The Confucian Notion of Jing (Respect), Sin Yee Chan, 2 : (...) 229-252Chong, Kim-chong, Zhuangzi and the Nature of Metaphor, 3 : 370-391Chung, Chai-sik, Between Principle and Situation: Contrasting Styles in the Japanese and Korean Traditions of Moral Culture, 2 : 253-280The Confucian Ideal of Harmony, Chenyang Li, 4 : 583-603The Confucian Notion of Jing.(Respect), Sin Yee Chan, 2 : 229-252The Conventional Status of Reflexive Awareness: What's at Stake in a Tibetan Debate? Jay L. Garfield, 2 : 201-228The Crisis of Knowledge in Islam (I): The Case of al-'āmirī, Paul L. Heck, 1 : 106-135The Crow and the Coconut: Accident, Coincidence, and Causation in the Yogavāiṣṭha, Nicholas Buxton, 3 : 392-408De Reu, Wim, Right Words Seem Wrong: Neglected Paradoxes in Early Chinese Philosophical Texts, 2 : 281-300The Desire You Are Required to Get Rid of: A Functionalist Analysis of Desire in the Bhaga-vadgītā, Christopher Framarin, 4 : 604-617Framarin, Christopher, The Desire You Are Required to Get Rid of: A Functionalist Analysis of Desire in the Bhagavadgītā, 4 : 604-617Garfield, Jay L., The Conventional Status of Reflexive Awareness: What's at Stake in a Tibetan Debate? 2 : 201-228Heck, Paul L., The Crisis of Knowledge in Islam (I): The Case of al-'ā mirī, 1 : 106-135Heidegger's Comportment toward East-West Dialogue, Lin Ma and Jaap van Brakel, 4 : 519-566Ho, Chien-hsing, Saying the Unsayable, 3 : 409-427Kantor, Hans-Rudolf, Ontological Indeterminacy and Its Soteriological Relevance: An Assessment of Mou Zongsan's (1909-1995) Interpretation of Zhiyi's (538-597) Tiantai Buddhism, 1 : 16-68Lai, Karyn, Li in the Analects: Training in Moral Competence and the Question of Flexibility, 1 : 69-83Li, Chenyang, The Confucian Ideal of Harmony, 4 : 583-603Li in the Analects: Training in Moral Competence and the Question of Flexibility, Karyn Lai, 1 : 69-83Ma, Lin, and Jaap van Brakel, Heidegger's Comportment toward East-West Dialogue, 4 : 519-566National Communion: Watsuji Tetsurō's Conception of Ethics, Power, and the Japanese Imperial State, Bernard Bernier, 1 : 84-105Ontological Indeterminacy and Its Soteriological Relevance: An Assessment of Mou Zongsan's (1909-1995) Interpretation of Zhiyi's (538- 597) Tiantai Buddhism, Hans-Rudolf Kantor, 1 : 16-68Right Words Seem Wrong: Neglected Paradoxes in Early Chinese Philosophical Texts, Wim De Reu, 2 : 281-300The Role of Time in the Structure of Chinese Logic, Jinmei Yuan, 1 : 136-152Sakya Pandita and the Status of Concepts, Jonathan Stoltz, 4 : 567-582Saying the Unsayable, Chien-hsing Ho, 3 : 409-427Schiltz, Elizabeth, Two Chariots: The Justification of the Best Life in the Katha Upanishad and Plato's Phaedrus, 3 : 451-468Spackman, John, The Tiantai Roots of Dōgen's Philosophy of Language and Thought, 3 : 428-450Stevenson, Frank W., Zhuangzi's Dao as Background Noise, 2 : 301-331Stoltz, Jonathan, Sakya Pandita and the Status of Concepts, 4 : 567-582The Tiantai Roots of Dōgen's Philosophy of Language and Thought, John Spackman, 3 : 428-450 [End Page 709]Two Chariots: The Justification of the Best Life in the Katha Upanishad and Plato's Phaedrus, Elizabeth Schiltz, 3 : 451-468van Brakel, Jaap, and Lin Ma, Heidegger's Comportment toward East-West Dialogue, 4 : 519-566Yuan, Jinmei, The Role of Time in the Structure of Chinese Logic, 1 : 136-152Zhuangzi and the Nature of Metaphor, Kim-chong Chong, 3 : 370-391Zhuangzi's Dao as Background Noise, Frank W. Stevenson, 2 : 301-331Book NotesFenner, David E. W., Introducing Aesthetics (note by James McRae), 3 : 515-516Introducing Aesthetics, by David E. W. Fenner (note by James McRae), 3 : 515-516McRae, James, a book... (shrink)

Part-of-speech tagging for English composition is the basis for automatic correction of English composition. The performance of the part-of-speech tagging system directly affects the performance of the marking and analysis of the correction system. Therefore, this paper proposes an automatic scoring model for English composition based on article part-of-speech tagging. First, use the convolutional neural network to extract the word information from the character level and use this part of the information in the coarse-grained learning layer. Secondly, the (...) class='Hi'>word-level vector is introduced, and the residual network is used to establish an information path to integrate the coarse-grained annotation and word vector information. Then, the model relies on the recurrent neural network to extract the overall information of the sequence data to obtain accurate annotation results. Then, the features of the text content are extracted, and the automatic scoring model of English composition is constructed by means of model fusion. Finally, this paper uses the English composition scoring competition data set on the international data mining competition platform Kaggle to verify the effect of the model. (shrink)

This replication study aims to investigate a potential bias toward addition in the German language, building upon previous findings of Winter and colleagues who identified a similar bias in English. Our results confirm a bias in word frequencies and binomial expressions, aligning with these previous findings. However, the analysis of distributional semantics based on word vectors did not yield consistent results for German. Furthermore, our study emphasizes the crucial role of selecting appropriate translational equivalents, highlighting the significance (...) of considering language‐specific factors when testing for such biases for languages other than English. (shrink)

Among the myriad of technical approaches and abstract guidelines proposed to the topic of AI bias, there has been an urgent call to translate the principle of fairness into the operational AI reality with the involvement of social sciences specialists to analyse the context of specific types of bias, since there is not a generalizable solution. This article offers an interdisciplinary contribution to the topic of AI and societal bias, in particular against the poor, providing a conceptual framework of the (...) issue and a tailor-made model from which meaningful data are obtained using Natural Language Processing word vectors in pretrained Google Word2Vec, Twitter and Wikipedia GloVe word embeddings. The results of the study offer the first set of data that evidences the existence of bias against the poor and suggest that Google Word2vec shows a higher degree of bias when the terms are related to beliefs, whereas bias is higher in Twitter GloVe when the terms express behaviour. This article contributes to the body of work on bias, both from and AI and a social sciences perspective, by providing evidence of a transversal aggravating factor for historical types of discrimination. The evidence of bias against the poor also has important consequences in terms of human development, since it often leads to discrimination, which constitutes an obstacle for the effectiveness of poverty reduction policies. (shrink)

Recent metaphor research has revealed that metaphor comprehension involves both categorization and comparison processes. This finding has triggered the following central question: Which property determines the choice between these two processes for metaphor comprehension? Three competing views have been proposed to answer this question: the conventionality view (Bowdle & Gentner, 2005), aptness view (Glucksberg & Haught, 2006b), and interpretive diversity view (Utsumi, 2007); these views, respectively, argue that vehicle conventionality, metaphor aptness, and interpretive diversity determine the choice between the categorization (...) and comparison processes. This article attempts to answer the question regarding which views are plausible by using cognitive modeling and computer simulation based on a semantic space model. In the simulation experiment, categorization and comparison processes are modeled in a semantic space constructed by latent semantic analysis. These two models receive word vectors for the constituent words of a metaphor and compute a vector for the metaphorical meaning. The resulting vectors can be evaluated according to the degree to which they mimic the human interpretation of the same metaphor; the maximum likelihood estimation determines which of the two models better explains the human interpretation. The result of the model selection is then predicted by three metaphor properties (i.e., vehicle conventionality, aptness, and interpretive diversity) to test the three views. The simulation experiment for Japanese metaphors demonstrates that both interpretive diversity and vehicle conventionality affect the choice between the two processes. On the other hand, it is found that metaphor aptness does not affect this choice. This result can be treated as computational evidence supporting the interpretive diversity and conventionality views. (shrink)

This paper describes a method for extracting importance of slides in a lecture review system. We introduce "index of importance" to quantitatively evaluate importance of slides. The index of importance is subjective evaluation value that is attached to each slide by lecturers. Firstly, the lecture review system extracts the index of importance of the slide by using a multi-layer neural network. In a MLN learning process, eight types of nonlinguistic informations, such as the presentation time of the slide, are used (...) as inputs and the index of importance given by lecturers are set as outputs. Secondly, the index of importance is modified by using the other MLN which has two types of inputs; one is the index of importance and the other is similarities between the slide and adjacent slides. The similarities are calculated with key-word vectors extracted by linguistic informations in slides. The experimental results showed that the index of importance extracted by the system is highly correlated with the index attached by lecturers. As a result, the lecture review system with the proposed extraction method can properly detect key slides and helps students to learn the contents of a lecture effectively. (shrink)

Advances in machine learning and natural language processing are revolutionizing the way we live, work, and think. As for any science, they are based on assumptions about what the world is, and how humans interact with it. In this paper, I discuss what is potentially one of these assumptions: structuralism, which states that all cultures share a hidden structure. I illustrate this assumption with political footprints: a machine-learning technique using pre-trained word vectors for political discourse analysis. I introduce (...) some of the benefits and limitations of structuralism when applied to machine learning, and the risks of exploiting a technology before establishing the validity of all its hypotheses. I consider how machine-learning techniques could evolve towards hybrid structuralism or post-structuralism, and how deeply these developments would impact cultural studies. (shrink)

While representation learning techniques have shown great promise in application to a number of different NLP tasks, they have had little impact on the problem of ontology matching. Unlike past work that has focused on feature engineering, we present a novel representation learning approach that is tailored to the ontology matching task. Our approach is based on embedding ontological terms in a high-dimensional Euclidean space. This embedding is derived on the basis of a novel phrase retrofitting strategy through which semantic (...) similarity information becomes inscribed onto fields of pre-trained word vectors. The resulting framework also incorporates a novel outlier detection mechanism based on a denoising autoencoder that is shown to improve performance. An ontology matching system derived using the proposed framework achieved an F-score of 94% on an alignment scenario involving the Adult Mouse Anatomical Dictionary and the Foundational Model of Anatomy ontology (FMA) as targets. This compares favorably with the best performing systems on the Ontology Alignment Evaluation Initiative anatomy challenge. We performed additional experiments on aligning FMA to NCI Thesaurus and to SNOMED CT based on a reference alignment extracted from the UMLS Metathesaurus. Our system obtained overall F-scores of 93.2% and 89.2% for these experiments, thus achieving state-of-the-art results. (shrink)

In this paper, we conduct an in-depth study of Japanese keyword extraction from news reports, train external computer document word sets from text preprocessing into word vectors using the Ship-gram model in the deep learning tool Word2Vec, and calculate the cosine distance between word vectors. In this paper, the sliding window in TextRank is designed to connect internal document information to improve the in-text semantic coherence. The main idea is to use not only the statistical (...) and structural features of words but also the semantic features of words extracted through word-embedding techniques, i.e., multifeature fusion, to obtain the importance weights of words themselves and the attraction weights between words and then iteratively calculate the final weight of each word through the graph model algorithm to determine the extracted keywords. To verify the performance of the algorithm, extensive simulation experimental studies were conducted on three different types of datasets. The experimental results show that the proposed keyword extraction algorithm can improve the performance by a maximum of 6.45% and 20.36% compared with the existing word frequency statistics and graph model methods, respectively; MF-Rank can achieve a maximum performance improvement of 1.76% compared with PW-TF. (shrink)

In view of the poor recommendation performance of traditional resource collaborative filtering recommendation algorithms, this article proposes a collaborative filtering recommendation model based on deep learning for art and MOOC resources. This model first uses embedding vectors based on the context of metapaths for learning. Embedding vectors based on the context of metapaths aggregate different metapath information and different MOOCs may have different preferences for different metapaths. Secondly, to capture this preference drift, the model introduces an attention mechanism, (...) which can improve the interpretability of the recommendation results. Then, by introducing the Laplacian matrix into the prior distribution of the hidden factor feature matrix, the relational network information is effectively integrated into the model. Finally, compared with the traditional model using the scoring matrix, the model in this article using text word vectors effectively alleviates the impact of data sparsity and greatly improves the accuracy of prediction. After analyzing the experimental results, compared with other algorithms, the resource collaborative filtering recommendation model proposed in this article has achieved better recommendation results, with good stability and scalability. (shrink)

Job seekers find themselves increasingly duped and misled by fraudulent job advertisements, posing a threat to their privacy, security and well-being. There is a clear need for solutions that can protect innocent job seekers. Existing approaches to detecting fraudulent jobs do not scale well, function like a black-box, and lack interpretability, which is essential to guide applicants’ decision-making. Moreover, commonly used lexical features may be insufficient as the representation does not capture contextual semantics of the underlying document. Hence, this paper (...) explores to what extent different categorizations of fraudulent jobs can be classified. In addition, this paper seeks to find what type of features are most relevant in classifying the type of fraudulent job. In this paper, we develop and validate a machine learning system for identifying identity theft, corporate identity theft and multi-level marketing amongst fraudulent job advertisements. We utilized four classes of features: empirical rule set-based features, bag-of-word models, most recent state-of-the-art word embeddings and transformer models for various machine learning classifiers. The machine learning models were validated by evaluating them on a publicly available job description dataset. Our results indicate that the word embeddings and transformer-based features consistently outperformed the handcrafted rule-set based features class. Ultimately, a Gradient Boosting classifier with a combination of empirical rule-set based features, parts-of-speech tags and bag-of-words vectors achieved the best performance with an F1-score of 0.88. (shrink)

Research on the construction of traditional information science methodology taxonomy is mostly conducted manually. From the limited corpus, researchers have attempted to summarize some of the research methodology entities into several abstract levels (generally three levels); however, they have been unable to provide a more granular hierarchy. Moreover, updating the methodology taxonomy is traditionally a slow process. In this study, we collected full-text academic papers related to information science. First, we constructed a basic methodology taxonomy with three levels by manual (...) annotation. Then, the word vectors of the research methodology entities were trained using the full-text data. Accordingly, the research methodology entities were clustered and the basic methodology taxonomy was expanded using the clustering results to obtain a methodology taxonomy with more levels. This study provides new concepts for constructing a methodology taxonomy of information science. The proposed methodology taxonomy is semi-automated; it is more detailed than conventional schemes and the speed of taxonomy renewal has been enhanced. (shrink)

This paper takes laptops as an example to carry out research on quantitative model of brand recognition based on sentiment analysis of big data. The basic idea is to use web crawler technology to obtain the most authentic and direct information of different laptop brands from first-line consumers from public spaces such as buyer reviews of major e-commerce platforms, including review time, text reviews, satisfaction ratings and relevant user information, etc., and then analyzes consumers’ sentimental tendencies and recognition status of (...) the product brands. This study extracted a total of 437,815 user reviews of laptops from e-commerce platforms from January 1, 2019 to December 31, 2021, and performed data preprocessing on the obtained review data, followed by sentiment dictionary construction, attribute expansion, text quantification and algorithm evaluation. This paper analyzed the information receiving and processing hierarchy of the quantitative model of brand recognition, discussed the interactive relationship between brand recognition and consumer sentiment, discussed the brand recognition bias, style and demand in the context of big data, and performed the sentiment statistics and dimension analysis in the quantitative model of brand recognition. The study results show that the quantitative model of brand recognition based on sentiment analysis of big data can transform and map the keywords in text to word vectors in the high-dimensional semantic space by performing unsupervised machine learning on the text based on artificial neural network computer bionic metaphors; the model can accumulate each brand-related buyer review in the corresponding brand recognition dimension, so as to obtain the value of each product in each dimension of brand recognition; finally, the model will add the values of each dimension of brand recognition, that is, obtain the relevant value of the sum of each brand recognition. The results of this paper may provide a reference for further research on the quantitative model of brand recognition based on sentiment analysis of big data. (shrink)

With the deepening of globalization, brand plays an important role in determining the competitiveness of enterprises. It is worth thinking about how to quantify the brand value reasonably to achieve the purpose of improving the competitiveness of enterprises. The research of commercial brands based on emotion analysis extracts the views of consumers on the evaluation data of brand attributes, analyzes the emotional tendency of consumers' views, and then helps enterprises adjust their production strategies. The purpose of emotion analysis is to (...) judge users' views and attitudes toward goods or services by analyzing texts. In this paper, the linear support vector machine model is used to extract and study the features in sentiment analysis. Then, the brand based on the fusion model is evaluated, and the experimental conclusions are drawn: the method of fusing the depth features extracted by word vector and the named entity extracted by CRF makes the brand effect of fusing emotional factors better than the feature extraction method only using CRF named entity recognition. It is proved that the model method proposed in this paper has a certain role in actual business. Feature fusion often combines shallow model methods and fuses various shallow feature screening technologies based on word segmentation results. This paper introduces fusion features and supplements feature vectors based on the results of the deep learning word vector model. Support Vector Machine maps feature vectors to some sample points in the space, finds a plane that can realize sample classification, and maximizes the distance between the two sample points closest to the plane in two types of samples, to maximize the classification performance and improve the generalization of the model. (shrink)

Text emotion analysis is an effective way for analyzing the emotion of the subjects’ anomie behaviors. This paper proposes a text emotion analysis framework based on word embedding and splicing. Bi-direction Convolutional Word Embedding Classification Framework can express the word vector in the text and embed the part of speech tagging information as a feature of sentence representation. In addition, an emotional parallel learning mechanism is proposed, which uses the temporal information of the parallel structure calculated by (...) Bi-LSTM to update the storage information through the gating mechanism. The convolutional layer can better extract certain components of sentences, which play a more significant role in the expression of emotion. To take advantage of convolution, a Convolutional Long Short-Term Memory network is designed to further improve the classification results. Experimental results show that compared with traditional LSTM model, the proposed text emotion analysis model has increased 3.3 and 10.9% F1 score on psychological and news text datasets, respectively. The proposed CBDM model based on Bi-LSTM and ConvLSTM has great value in practical applications of anomie behavior analysis. (shrink)

Advances in machine learning and natural language processing are revolutionizing the way we live, work, and think. As for any science, they are based on assumptions about what the world is, and how humans interact with it. In this paper, I discuss what is potentially one of these assumptions: structuralism, which states that all cultures share a hidden structure. I illustrate this assumption with political footprints: a machine-learning technique using pre-trained word vectors for political discourse analysis. I introduce (...) some of the benefits and limitations of structuralism when applied to machine learning, and the risks of exploiting a technology before establishing the validity of all its hypotheses. I consider how machine-learning techniques could evolve towards hybrid structuralism or post-structuralism, and how deeply these developments would impact cultural studies. (shrink)

How to strengthen emergency management and improve the ability to prevent and respond to emergencies is an important part of building a harmonious socialist society. This paper proposes a domain emotion dictionary construction method for network public opinion analysis of public emergencies. Using the advantages of corpus and semantic knowledge base, this paper extracts the seed words based on the large-scale network public opinion corpus and combined with the existing emotion dictionary, trains the word vector through the word2vec model (...) in deep learning, expands the emotion words, and obtains the candidate emotion words according to the semantic similarity calculation, So as to generate a domain emotion dictionary. The accuracy rate of emotion discrimination by the emotion dictionary constructed in this paper is 0.86, the recall rate is 0.92. Through the verification of accuracy and recall rate, the construction method proposed in this paper has good accuracy and reliability. Because of the great differences in different experiences and situations of different groups, there will be great differences in views and perspectives on the same event. The key to prevent the public from blindly following the crowd should be to reach groups close to emotional distance, and targeted prevention and control of public opinion can be conducted according to different characteristics of different groups. (shrink)

Cultural development is often reflected in the emotional expression of various cultural carriers, such as literary works, movies, etc. Therefore, the cultural development can be analyzed through emotion analysis of the text, so as to sort out its context and obtain its development dynamics. This paper proposes a text emotion analysis method based on deep learning. The traditional neural network model mainly deals with the classification task of short texts in the form of word vectors, which causes the (...) model to rely too much on the accuracy of word segmentation. In addition, the short texts have the characteristics of short corpus and divergent features. A text emotion classification model combing the Bidirectional Encoder Representations from Transformers and Bi-directional Long Short-Term Memory is developed in this work. First, the BERT model is used to convert the trained text into a word-based vector representation. Then, the generated word vector is employed as the input of the BiLSTM to obtain the semantic representation of the context of the relevant word. By adding random dropout, the mechanism prevents the model from overfitting. Finally, the extracted feature vector is input to the fully connected layer, and the emotion category to which the text belongs is calculated through the Softmax function. Experiments show that in processing short texts, the proposed model based on BERT-BiLSTM is more accurate and reliable than the traditional neural network model using word vectors. The proposed method has a better analysis effect on the development of western culture. (shrink)

Combining the communicative language competence model and the perspective of multimodal research, this research proposes a research framework for oral communicative competence under the multimodal perspective. This not only truly reflects the language communicative competence but also fully embodies the various contents required for assessment in the basic attributes of spoken language. Aiming at the feature sparseness of the user evaluation matrix, this paper proposes a feature weight assignment algorithm based on the English spoken category keyword dictionary and user search (...) records. The algorithm is mainly based on the self-built English oral category classification dictionary and converts the user’s query vector into a user-English-speaking type vector. Through the calculation rules proposed in this paper, the target user’s preference score for a specific type of spoken English is obtained, and this score is assigned to the unrated item of the original user’s feature matrix as the initial starting score. At the same time, in order to solve the problem of insufficient user similarity calculation accuracy, a user similarity calculation algorithm based on “Synonyms Cilin Extended Edition” and search records is proposed. The algorithm introduces “Synonyms Cilin” to calculate the correlation between the semantic items, vocabulary, and query vector in the user query record to obtain the similarity between users and finally gives a user similarity calculation that integrates user ratings and query vectors method. For the task of Chinese grammar error correction, this article uses two methods of predicting the relationship between words in the corpus, Word2Vec and GloVe, to train the word vectors of different dimensions and use the word vectors to represent the text features of the experimental samples, avoiding sentences brought by word segmentation. On the basis of word vectors, the advantages and disadvantages of CNN, LSTM, and SVM models in this shared task are analyzed through experimental data. The comparative experiment shows that the method in this paper has achieved relatively good results. (shrink)

We have developed a knowledge base of words as a tool to measure the semantic similarity between words. In this paper, we evaluate the knowledge base of words comparing with thesauruses, which are commonly used for measuring similarity. Thesauruses of NIHONGO-GOI-TAIKEI and Japan Electronic Dictionary are selected for the evaluation. For similarity calculation methods using thesauruses, we adopt a newly proposed method, in which each word is represented with vector using the structural feature of thesauruses and the degree of (...) similarity between words is calculated by the inner product of their vectors, in addition to traditional methods based on the path length between categories or the depth of the subsumer. Evaluation is carried out through the two methods, that is, a traditional method based on human rating and the method we have already proposed, feasible for evaluating automatically without human judgment. Evaluation result shows that the knowledge base of word is superior to the both thesauruses as measurement tools, and the proposed calculation method outperforms the traditional ones. The result also shows that our evaluation method is a practical one, by investigating the correlation of both methods. (shrink)