In this paper, we showcase our research on the use of ontologies and information extraction for the purpose of modeling damages incurred on car bodies. With the increasing use of technology in the automotive industry, it is important to have a standardized and efficient way of documenting and analyzing car damage reports. Most existing reports are unstructured, and there is a lack of standardization in describing the damage. To address this issue, we have developed a domain ontology for (...) car damage modeling (OCD),11 industryportal.enit.fr/ontologies/OCD,22 github.com/OntologyCarDamage/OCD and proposed an end-to-end system to extract information from French automotive reports. The information extraction process involves using named entity recognition (NER) and relationship extraction (RE) techniques to identify and extract relevant information from the reports. Then, the extracted information is used to populate the OCD ontology, allowing a structured and standardized representation of the damage information. The proposed system was tested on a real dataset of automotive reports and showed promising results. (shrink)

This paper concerns an information extraction process for building a dynamic legislation network from legal documents. Unlike supervised learning approaches which require additional calculations, the idea here is to apply information extraction methodologies by identifying distinct expressions in legal text in order to extract network information. The study highlights the importance of data accuracy in network analysis and improves approximate string matching techniques to produce reliable network data-sets with more than 98% precision and recall. The (...) applications and the complexity of the created dynamic legislation network are also discussed and challenged. (shrink)

The number of available legal documents has presented an enormous growth in recent years, and the digital processing of such materials is prompting the necessity of systems that support the automatic relevant information extraction. This work presents a system for ontology-based information extraction from natural language texts, able to identify a set of legal events. The system is based on an innovative methodology based on domain ontology of legal events and a set of linguistic rules, integrated (...) through inference mechanism, resulting in a flexible approach and scalable approach. A case study with the use of documents from the Superior Court in Brazil is related, with satisfactory results in precision and recall. (shrink)

Most current statistical natural language processing models use only local features so as to permit dynamic programming in inference, but this makes them unable to fully account for the long distance structure that is prevalent in language use. We show how to solve this dilemma with Gibbs sam- pling, a simple Monte Carlo method used to perform approximate inference in factored probabilistic models. By using simulated annealing in place of Viterbi decoding in sequence models such as HMMs, CMMs, and CRFs, (...) it is possible to incorporate non-local structure while preserving tractable inference. We use this technique to augment an existing CRF-based information extraction system with long-distance dependency models, enforcing label consistency and extraction template consistency constraints. This technique results in an error reduction of up to 9% over state-of-the-art systems on two established information extraction tasks. (shrink)

We initially describe a feature-rich discriminative Conditional Random Field (CRF) model for Information Extraction in the workshop announcements domain, which offers good baseline performance in the PASCAL shared task. We then propose a method for leveraging domain knowledge in Information Extraction tasks, scoring candidate document labellings as one-value-per-field templates according to domain feasibility after generating sample labellings from a trained sequence classifier. Our relational models evaluate these templates according to our intuitions about agreement in the domain: (...) workshop acronyms should resemble their names, workshop dates occur after paper submission dates. These methods see a 5% f-score improvement in fields retrieved when sampling labellings from a Maximum-Entropy Markov Model, however we do not observe improvement over a CRF model. We discuss reasons for this, including the problem of recovering all field instances from a best template, and propose future work in adapting such a model to the CRF, a better standalone system. (shrink)

Speech is a fundamental means of human communication. Design and construction are social activities. We argue that designers and builders generate and develop concepts through dialogue. These communicative events are typically not captured. Consequently, knowledge transfer and reuse opportunities are missed. Our objective is to capture and mine rich, contextual, social communicative events for further knowledge reuse. We present a methodology and prototype called I-Dialogue that: (1) captures the knowledge generated during informal communicative events through dialogue, sketching and gestures in (...) the form of unstructured digital design knowledge corpus; (2) adds structure to the unstructured digital knowledge corpus; and (3) processes the corpus using an innovative notion disambiguation algorithm in support of knowledge retrieval. The paper concludes with results of evaluation experiments with I-Dialogue using a testbed of design–construction projects. (shrink)

This study seeks to explicate the philosophical foundations and theoretical outlines of grey systems theory by focusing on human perception, cognition, and understanding processes and by considering their functions in the process of producing knowledge. Primarily, the study investigates the processes of perception, cognition, and understanding, as well as their dynamicity. Then, it is explained how knowledge is produced through the interpretation/understanding of information and data and through the dynamicity governing this process. The findings reveal that human perception, cognition, (...) and understanding perpetually remain grey and imperfect, while lost sensatory data mark the very first aspect of greyness in such human capabilities. Furthermore, any piece of data, as a discrete and single entity, represents a determinate fact, symbol or signal from the world, while any set of data, no matter how large, remains incomplete and imperfect, and human beings always interpret inadequate sets of data in the world. Therefore, information and knowledge always remain grey and uncertain because they deeply rely on subjective understandings/interpretations and work with imperfect inputs and sets of data. The impact of knowledge on action and interaction and their effects on the world are some factors adding to the dynamicity of the world. Constant change in world data, outdated knowledge, defects in datasets, and human biases in understanding all confirm the infinitely grey nature of human knowledge of the world. (shrink)

This book reflects the growing influence of corpus linguistics in a variety of areas such as lexicography, translation studies, genre analysis, and language ...

Does cultural evolution happen by a process of copying or replication? And how exactly does cultural transmission compare with that paradigmatic case of replication, the copying of DNA in living cells? Theorists of cultural evolution are divided on these issues. The most important objection to the replication model has been leveled by Dan Sperber and his colleagues. Cultural transmission, they argue, is almost always reconstructive and transformative, while strict ‘replication’ can be seen as a rare limiting case at most. By (...) means of some thought experiments and intuition pumps, I clear up some confusion about what qualifies as ‘replication’. I propose a distinction between evocation and extraction of cultural information, applying these concepts at different levels of resolution. I defend a purely abstract and information-theoretical definition of replication, while rejecting more material conceptions. In the end, even after taking Sperber’s valuable and important points on board, the notion of cultural replication remains a valid and useful one. This is fortunate, because we need it for certain explanatory projects. (shrink)

This article aims to explore representation of the content knowledge of historical Malay manuscripts by extracting the event features using an event ontology framework. The manuscript used during the testing is Sulalatus Salatin by Abdul Ahmad Samad and it was published at University of Malaya Digital Library database. In aligning to a domain-specific ontology, the Simple Event Model model is adopted and an event-based ontology for historical Malay manuscripts is designed. Information extraction approach is done manually to extract (...) events from the manuscript and mapped into Protégé editor. Competency questions were constructed and submitted to the Protégé editor using SPARQL to check the ontology capability of providing answers as well as to examine its correctness. Event-based ontology model assists in discovering and representing the content knowledge of historical Malay manuscripts and supports organisation of knowledge. All the main concepts are extracted from selected Malay manuscript and 17 concepts used to develop the event-based ontology model. The knowledge was verified by three domain experts in Malay manuscript. In the findings, the interrater reliability for Event and Actor instances is 84%, which means 16% of instances and its type are incorrect and need amendment. For Place, interrater reliability is 95% and 99% for Role. Meanwhile, the experts achieved 100% agreement for Time. In addition, the experts agreed that the concepts, properties and instances for Malay Manuscript Ontology and complied with the criteria of consistency, completeness, conciseness, expandability and ease of use. The development of the event-based model of an ontology-based system with a high level of semantic granularity reflects the various cultural riches and intellectual aspect stored in Malay manuscripts. This will enable systematic research of the knowledge embedded in the manuscripts and make it widely and easily accessible by everyone. (shrink)

Convolutional neural networks (CNNs) are increasingly widely used in psychology and neuroscience to predict how human minds and brains respond to visual images. Typically, CNNs represent these images using thousands of features that are learned through extensive training on image datasets. This raises a question: How many of these features are really needed to model human behavior? Here, we attempt to estimate the number of dimensions in CNN representations that are required to capture human psychological representations in two ways: (1) (...) directly, using human similarity judgments and (2) indirectly, in the context of categorization. In both cases, we find that low-dimensional projections of CNN representations are sufficient to predict human behavior. We show that these low-dimensional representations can be easily interpreted, providing further insight into how people represent visual information. A series of control studies indicate that these findings are not due to the size of the dataset we used and may be due to a high level of redundancy in the features appearing in CNN representations. (shrink)

This article addresses the problem of automatically extracting legal indices which express the important contents of legal documents. Legal indices are not limited to single-word keywords and compound-word keywords, they are also clause keywords. We approach index extraction using structural information of Japanese sentences, i.e. chunks and clauses. Based on the assumption that legal indices are composed of important tokens from the documents, extracting legal indices is treated as a problem of collecting chunks and clauses that contain as (...) many important tokens as possible. Each token is assigned a weight which is a statistical score, e.g. TF–IDF and Okapi BM25, to indicate its importance. The importance of a chunk or clause is determined based on the average weight of tokens included in that chunk or clause. Then, highly weighted chunks and clauses are recognized as the indices for legal documents. The experimental results on Japanese National Pension Act data show that our proposed method achieves better performance than TextRank, the most popular unsupervised method in extracting single-word and compound-word keywords. In addition, this approach is also applicable to extract clause keywords with high performance. (shrink)

Appellate Court Modifications Extraction consists of, given an Appellate Court decision, identifying the proposed modifications by the upper Court of the lower Court judge’s decision. In this work, we propose a system to extract Appellate Court Modifications for Portuguese. Information extraction for legal texts has been previously addressed using different techniques and for several languages. Our proposal differs from previous work in two ways: our corpus is composed of Brazilian Appellate Court decisions, in which we look for (...) a set of modifications provided by the Court; and to automatically extract the modifications, we use a traditional Machine Learning approach and a Deep Learning approach, both as alternative solutions and as a combined solution. We tackle the Appellate Court Modifications Extraction task, experimenting with a wide variety of methods. In order to train and evaluate the system, we have built the KauaneJunior corpus, using public data disclosed by the Appellate State Court of Rio de Janeiro jurisprudence database. Our best method, which is a Bidirectional Long Short-Term Memory network combined with Conditional Random Fields, obtained an \ score of 94.79%. (shrink)

The rapid increase in COVID-19 cases has become the symbol of fear, anxiety, and panic among people around the globe. Mass media has played an active role in community education by addressing the health information of this pandemic. People interact by sharing their ideas and feelings through social media platforms. There is a considerable need to implement different measures and better perceive COVID-19 pertinent facts and information by demystifying public sentiments. In this study, the Quarantine Life dataset of (...) thousand tweets is based on #Quarantine, #Quarantine Days, #Quarantine Life, #My Pandemic Plan, and #Quarantine and Chill from January to September 2020 has been collected from Twitter. The extracted data have been scrubbed through preprocessing techniques. The sentiments and topics extracted from tweets have been analyzed through the TEXT BLOB, VADER, and AFFIN approach. Results show that people were distressed and fearful due to the COVID-19 pandemic. However, most people enjoyed by playing games, watching movies, and reading books during the lockdown period. According to the present meta-analysis, physical activity interventions are beneficial for patients with dementia in terms of cognition. The proposed framework illustrates the insight impact of COVID-19 on human physiological and mainly focuses on the evaluation of sentiment dynamics at the topical level. (shrink)

This article reviews existing empirical research on the peak-and-end rule. This rule states that people's global evaluations of past affective episodes can be well predicted by the affect experienced during just two moments: the moment of peak affect intensity and the ending. One consequence of the peak-and-end rule is that the duration of affective episodes is largely neglected. Evidence supporting the peak-and-end rule is robust, but qualified. New directions for future work in this emerging area of study are outlined. In (...) particular, the personal meanings associated with specific moments and with specific emotions should be assessed. It is hypothesised that moments rich with self-relevant information will dominate people's global evaluations of past affective episodes. The article concludes with a discussion of ways to measure and optimise objective happiness. (shrink)

Keyword extraction refers to the process of selecting most significant, relevant, and descriptive terms as keywords, which are present inside a single document. Keyword extraction has major applications in the information retrieval domain, such as analysis, summarization, indexing, and search, of documents. In this paper, we present a novel supervised technique for extraction of keywords from medium-sized documents, namely Corpus-based Contextual Semantic Smoothing. CCSS extends the concept of Contextual Semantic Smoothing, which considers term usage patterns in (...) similar texts to improve term relevance information. We introduce four more features beyond CSS as our novel contributions in this work. We systematically compare the performance of CCSS with other techniques, when implemented over INSPEC dataset, where CCSS outperforms all state-of-the-art keyphrase extraction techniques presented in the literature. (shrink)

We describe research carried out as part of a text summarisation project for the legal domain for which we use a new XML corpus of judgments of the UK House of Lords. These judgments represent a particularly important part of public discourse due to the role that precedents play in English law. We present experimental results using a range of features and machine learning techniques for the task of predicting the rhetorical status of sentences and for the task of selecting (...) the most summary-worthy sentences from a document. Results for these components are encouraging as they achieve state-of-the-art accuracy using robust, automatically generated cue phrase information. Sample output from the system illustrates the potential of summarisation technology for legal information management systems and highlights the utility of our rhetorical annotation scheme as a model of legal discourse, which provides a clear means for structuring summaries and tailoring them to different types of users. (shrink)

Traditional methods for deriving property-based representations of concepts from text have focused on either extracting only a subset of possible relation types, such as hyponymy/hypernymy (e.g., car is-a vehicle) or meronymy/metonymy (e.g., car has wheels), or unspecified relations (e.g., car—petrol). We propose a system for the challenging task of automatic, large-scale acquisition of unconstrained, human-like property norms from large text corpora, and discuss the theoretical implications of such a system. We employ syntactic, semantic, and encyclopedic information to guide our (...) extraction, yielding concept-relation-feature triples (e.g., car be fast, car require petrol, car cause pollution), which approximate property-based conceptual representations. Our novel method extracts candidate triples from parsed corpora (Wikipedia and the British National Corpus) using syntactically and grammatically motivated rules, then reweights triples with a linear combination of their frequency and four statistical metrics. We assess our system output in three ways: lexical comparison with norms derived from human-generated property norm data, direct evaluation by four human judges, and a semantic distance comparison with both WordNet similarity data and human-judged concept similarity ratings. Our system offers a viable and performant method of plausible triple extraction: Our lexical comparison shows comparable performance to the current state-of-the-art, while subsequent evaluations exhibit the human-like character of our generated properties. (shrink)

Automatic text summarization extracts information from a source text and presents it to the user in a condensed form while preserving its primary content. Many text summarization approaches have been investigated in the literature for highly resourced languages. At the same time, ATS is a complicated and challenging task for under-resourced languages like Malayalam. The lack of a standard corpus and enough processing tools are challenges when it comes to language processing. In the absence of a standard corpus, we (...) have developed a dataset consisting of Malayalam news articles. This article proposes an extractive topic modeling-based multi-document text summarization approach for Malayalam news documents. We first cluster the contents based on latent topics identified using the latent Dirichlet allocation topic modeling technique. Then by adopting vector space model, the topic vector and sentence vector of the given document are generated. According to the relevant status value, sentences are ranked between the document’s topic and sentence vectors. The summary obtained is optimized for non-redundancy. Evaluation results on Malayalam news articles show that the summary generated by the proposed method is closer to the human-generated summaries than the existing text summarization methods. (shrink)

We report on an experiment examining whether individuals can solve a simple signal extraction problem of the type found in models with imperfect information. In one treatment, subjects must form point predictions based on observing both public and private signals, while in another they receive the same information but must decide on the weight to attach to each signal, which then determines their point prediction. We find that, at the aggregate level, signal extraction provides a good (...) characterization of subjects’ behavior in both treatments, but at the individual level, there is considerable heterogeneity in subjects’ ability to perform signal extraction. (shrink)

Ongoing electroencephalography signals are recorded as a mixture of stimulus-elicited EEG, spontaneous EEG and noises, which poses a huge challenge to current data analyzing techniques, especially when different groups of participants are expected to have common or highly correlated brain activities and some individual dynamics. In this study, we proposed a data-driven shared and unshared feature extraction framework based on nonnegative and coupled tensor factorization, which aims to conduct group-level analysis for the EEG signals from major depression disorder patients (...) and healthy controls when freely listening to music. Constrained tensor factorization not only preserves the multilinear structure of the data, but also considers the common and individual components between the data. The proposed framework, combined with music information retrieval, correlation analysis, and hierarchical clustering, facilitated the simultaneous extraction of shared and unshared spatio-temporal-spectral feature patterns between/in MDD and HC groups. Finally, we obtained two shared feature patterns between MDD and HC groups, and obtained totally three individual feature patterns from HC and MDD groups. The results showed that the MDD and HC groups triggered similar brain dynamics when listening to music, but at the same time, MDD patients also brought some changes in brain oscillatory network characteristics along with music perception. These changes may provide some basis for the clinical diagnosis and the treatment of MDD patients. (shrink)

This article describes the Vaccine/Injury Project Corpus, a collection of legal decisions awarding or denying compensation for health injuries allegedly due to vaccinations, together with models of the logical structure of the reasoning of the factfinders in those cases. This unique corpus provides useful data for formal and informal logic theory, for natural-language research in linguistics, and for artificial intelligence research. More importantly, the article discusses lessons learned from developing protocols for manually extracting the logical structure and generating the logic (...) models. It identifies sub-tasks in the extraction process, discusses challenges to automation, and provides insights into possible solutions for automation. In particular, the framework and strategies developed here, together with the corpus data, should allow “top–down” and contextual approaches to automation, which can supplement “bottom-up” linguistic approaches. Illustrations throughout the article use examples drawn from the Corpus. (shrink)

Since the early 1990s, the extractive industries have increasingly valued corporate social responsibility in the communities where they operate. More recently, these industries have begun to recognize the importance of adapting CSR efforts to unique local contexts rather than applying a one-size-fits-all model. However, firms understand local context to mean culture and treat the physical properties of the host region—topography, geology, hydrology, and climate—as the exclusive purview of mineral geologists and engineers. In this article, we examine the organization of CSR (...) at two industrial-scale gold mines in Guatemala, owned by the same firm, which yielded starkly distinct levels of support among host community residents. We develop the idea of social terrain to convey the way in which the biophysical environment informs local social relations and imbues phenomena with particular social meanings. We argue that firms must account for social terrain in organizing for CSR. The literature struggles to provide guidelines for identifying and understanding stakeholders. Social terrain, we argue, can begin to bridge this gap between theory and practice. (shrink)

How should we combine disagreeing expert judgments on the likelihood of an event? A common solution is simple averaging, which allows independent individual errors to cancel out. However, judgments can be correlated due to an overlap in their information, resulting in a miscalibration in the simple average. Optimal weights for weighted averaging are typically unknown and require past data to estimate reliably. This paper proposes an algorithm to aggregate probabilistic judgments under shared information. Experts are asked to report (...) a prediction and a meta-prediction. The latter is an estimate of the average of other individuals’ predictions. In a Bayesian setup, I show that if average prediction is a consistent estimator, the percentage of predictions and meta-predictions that exceed the average prediction should be the same. An “overshoot surprise” occurs when the two measures differ. The Surprising Overshoot algorithm uses the information revealed in an overshoot surprise to correct for miscalibration in the average prediction. Experimental evidence suggests that the algorithm performs well in moderate to large samples and in aggregation problems where individuals disagree in their predictions. (shrink)

Summarization of legal case judgement documents is a practical and challenging problem, for which many summarization algorithms of different varieties have been tried. In this work, rather than developing yet another summarization algorithm, we investigate if intelligently ensembling (combining) the outputs of multiple (base) summarization algorithms can lead to better summaries of legal case judgements than any of the base algorithms. Using two datasets of case judgement documents from the Indian Supreme Court, one with extractive gold standard summaries and the (...) other with abstractive gold standard summaries, we apply various ensembling techniques on summaries generated by a wide variety of summarization algorithms. The ensembling methods applied range from simple voting-based methods to ranking-based and graph-based ensembling methods. We show that many of our ensembling methods yield summaries that are better than the summaries produced by any of the individual base algorithms, in terms of ROUGE and METEOR scores. (shrink)