This paper presents the first use of a computational model of natural logic—a system of logical inference which operates over natural language—for textual inference. Most current approaches to the PAS- CAL RTE textual inference task achieve robustness by sacrificing semantic precision; while broadly effective, they are easily confounded by ubiquitous inferences involving monotonicity. At the other extreme, systems which rely on first-order logic and theorem proving are precise, but excessively brittle. This work aims at a middle way. Our system finds (...) a low-cost edit sequence which transforms the premise into the hypothesis; learns to classify entailment relations across atomic edits; and composes atomic entailments into a top-level entailment judgment. We provide the first reported results for any system on the FraCaS test suite. We also evaluate on RTE3 data, and show that hybridizing an existing RTE system with our natural logic system yields significant performance gains. (shrink)

I wish to present a codi cation of syntactic approaches to dealing with ergative languages and argue for the correctness of one particular approach, which I will call the Inverse Grammatical Relations hypothesis.1 I presume familiarity with the term `ergativity', but, brie y, many languages have ergative case marking, such as Burushaski in (1), in contrast to the accusative case marking of Latin in (2). More generally, if we follow Dixon (1979) and use A to mark the agent-like (...) argument of a transitive verb, O to mark the patient-like argument of a transitive verb, and S to mark the single argument of an intransitive verb, then we can call ergative any subsystem of a language that groups S and O in contrast to A, as shown in (3). (shrink)

We propose an approach to natural language inference based on a model of natural logic, which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. We greatly extend past work in natural logic, which has focused solely on semantic containment and monotonicity, to incorporate both semantic exclusion and implicativity. Our system decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical entailment relation for each edit using a statistical classifier; (...) propagates these relations upward through a syntax tree according to semantic properties of intermediate nodes; and composes the resulting entailment relations across the edit sequence. We evaluate our system on the FraCaS test suite, and achieve a 27% reduction in error from previous work. We also show that hybridizing an existing RTE system with our natural logic system yields significant gains on the RTE3 test suite. (shrink)

The same categorical phenomena which are attributed to hard grammatical constraints in some languages continue to show up as statistical preferences in other languages, motivating a grammatical model that can account for soft constraints. The effects of a hierarchy of person (1st, 2nd 3rd) on grammar are categorical in some languages, most famously in languages withError: Illegal entry in bfrange block in ToUnicode CMap inverse systems, but also in languages with person restrictions on passivization. In Lummi, for example, the (...) person of the subject argument cannot be lower than the person of a nonsubject argument. If this would happen in the active, passivization is obligatory; if it would happen in the passive, the active is obligatory (Jelinek and Demers 1983). These facts follow from the theory of harmonic alignment in OT: constraints favoring the harmonic association of prominent person (1st, 2nd) with prominent syntactic function (subject) are hypothesized to be present as subhierarchies of the grammars of all languages, but to vary in their effects across languages depending on their interactions with other constraints (Aissen 1999). There is a statistical reflection of these hierarchies in English. The same disharmonic person/argument associations which are avoided categorically in languages like Lummi by making passives either impossible or obligatory, are avoided in the SWITCHBOARD corpus of spoken English by either depressing or elevating the frequency of passives relative to actives. The English data can be grammatically analyzed within the stochastic OT framework (Boersma 1998, Boersma and Hayes 2001) in a way which provides a principled and unifying explanation for their relation to the crosslinguistic categorical person effects studied by Aissen (1999). (shrink)

Grammatical theory has long wrestled with the fact that causative constructions exhibit properties of both single words and complex phrases. However, as Paul Kiparsky has observed, the distribution of such properties of causatives is not arbitrary: ‘construal’ phenomena such as honorification, anaphor and pronominal binding, and quantifier ‘floating’ typically behave as they would if causatives were syntactically complex, embedding constructions; whereas case marking, agreement and word order phenomena all point to the analysis of causatives as single lexical items.1 Although (...) an analysis of causatives in terms of complex syntactic structures has frequently been adopted in an attempt to simplify the mapping to semantic structure, we believe that motivating syntactic structure based on perceived semantics is questionable because in general a syntax/semantics homomorphism cannot be maintained without vitiating syntactic theory (Miller 1991). Instead, we sketch a strictly lexical theory of Japanese causatives that deals with the evidence offered for a complex phrasal analysis. Such an analysis makes the phonology, morphology and syntax parallel, while a mismatch occurs with the semantics. The conclusions we will reach are given in (1). (shrink)

adjacent phrases, but they typically lack the ability to perform the kind of long-distance reorderings possible with syntax-based systems. In this paper, we present a novel hierarchical phrase reordering model aimed at improving non-local reorderings, which seamlessly integrates with a standard phrase-based system with little loss of computational efficiency. We show that this model can successfully handle the key examples often used to motivate syntax-based systems, such as the rotation of a prepositional phrase around a noun phrase. (...) We contrast our model with reordering models commonly used in phrase-based systems, and show that our approach provides statistically significant BLEU point gains for two language pairs: Chinese-English (+0.53 on MT05 and +0.71 on MT08) and Arabic-English (+0.55 on MT05). (shrink)

We present a novel algorithm for the fast computation of PageRank, a hyperlink-based estimate of the “importance” of Web pages. The original PageRank algorithm uses the Power Method to compute successive iterates that converge to the principal eigenvector of the Markov matrix representing the Web link graph. The algorithm presented here, called Quadratic Extrapolation, accelerates the convergence of the Power Method by periodically subtracting off estimates of the nonprincipal eigenvectors from the current iterate of the Power Method. In Quadratic Extrapolation, (...) we take advantage of the fact that the first eigenvalue of a Markov matrix is known to be 1 to compute the nonprincipal eigenvectors using successive iterates of the Power Method. Empirically, we show that using Quadratic Extrapolation speeds up PageRank computation by 50- 300% on a Web graph of 80 million nodes, with minimal overhead. (shrink)

Automatically clustering web pages into semantic groups promises improved search and browsing on the web. In this paper, we demonstrate how user-generated tags from largescale social bookmarking websites such as del.icio.us can be used as a complementary data source to page text and anchor text for improving automatic clustering of web pages. This paper explores the use of tags in 1) K-means clustering in an extended vector space model that includes tags as well as page text and 2) a novel (...) generative clustering algorithm based on latent Dirichlet allocation that jointly models text and tags. We evaluate the models by comparing their output to an established web directory. We find that the naive inclusion of tagging data improves cluster quality versus page text alone, but a more principled inclusion can substantially improve the quality of all models with a statistically signifi- cant absolute F-score increase of 4%. The generative model outperforms K-means with another 8% F-score increase. (shrink)

A desirable quality of a coreference resolution system is the ability to handle transitivity constraints, such that even if it places high likelihood on a particular mention being coreferent with each of two other mentions, it will also consider the likelihood of those two mentions being coreferent when making a final assignment. This is exactly the kind of constraint that integer linear programming (ILP) is ideal for, but, surprisingly, previous work applying ILP to coreference resolution has not encoded this (...) type of constraint. We train a coreference classifier over pairs of mentions, and show how to encode this type of constraint on top of the probabilities output from our pairwise classifier to extract the most probable legal entity assignments. We present results on two commonly used datasets which show that enforcement of transitive closure consistently improves performance, including improvements of up to 3.6% using the b3 scorer, and up to 16.5% using cluster f-measure. (shrink)

Many named entities contain other named entities inside them. Despite this fact, the field of named entity recognition has almost entirely ignored nested named entity recognition, but due to technological, rather than ideological reasons. In this paper, we present a new technique for recognizing nested named entities, by using a discriminative constituency parser. To train the model, we transform each sentence into a tree, with constituents for each named entity (and no other syntactic structure). We present results on both (...) newspaper and biomedical corpora which contain nested named entities. In three out of four sets of experiments, our model outperforms a standard semi-CRF on the more traditional top-level entities. At the same time, we improve the overall F-score by up to 30% over the flat model, which is unable to recover any nested entities. (shrink)

Many factors are thought to increase the chances of misrecognizing a word in ASR, including low frequency, nearby disfluencies, short duration, and being at the start of a turn. However, few of these factors have been formally examined. This paper analyzes a variety of lexical, prosodic, and disfluency factors to determine which are likely to increase ASR error rates. Findings include the following. (1) For disfluencies, effects depend on the type of disfluency: errors increase by up to 15% (absolute) for (...) words near fragments, but decrease by up to 7.2% (absolute) for words near repetitions. This decrease seems to be due to longer word duration. (2) For prosodic features, there are more errors for words with extreme values than words with typical values. (3) Although our results are based on output from a system with speaker adaptation, speaker differences are a major factor influencing error rates, and the effects of features such as frequency, pitch, and intensity may vary between speakers. (shrink)

Probabilistic methods are providing new explanatory approaches to fundamental cognitive science questions of how humans structure, process and acquire language. This review examines probabilistic models defined over traditional symbolic structures. Language comprehension and production involve probabilistic inference in such models; and acquisition involves choosing the best model, given innate constraints and linguistic and other input. Probabilistic models can account for the learning and processing of language, while maintaining the sophistication of symbolic models. A recent burgeoning of theoretical developments and online (...) corpus creation has enabled large models to be tested, revealing probabilistic constraints in processing, undermining acquisition arguments based on a perceived poverty of the stimulus, and suggesting fruitful links with probabilistic theories of categorization and ambiguity resolution in perception. (shrink)

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization provides conceptual simplicity, straightforward opportunities for separately improving the component models, and a level of performance comparable to similar, non-factored models. Most importantly, unlike other modern parsing models, the factored model admits an extremely effective A* parsing algorithm, which enables efficient, exact inference.

This paper presents empirical studies and closely corresponding theoretical models of the performance of a chart parser exhaustively parsing the Penn Treebank with the Treebank’s own CFG grammar. We show how performance is dramatically affected by rule representation and tree transformations, but little by top-down vs. bottom-up strategies. We discuss grammatical saturation, including analysis of the strongly connected components of the phrasal nonterminals in the Treebank, and model how, as sentence length increases, the effective grammar rule size increases as (...) regions of the grammar are unlocked, yielding super-cubic observed time behavior in some configurations. (shrink)

We present a generative distributional model for the unsupervised induction of natural language syntax which explicitly models constituent yields and contexts. Parameter search with EM produces higher quality analyses than previously exhibited by unsupervised systems, giving the best published unsupervised parsing results on the ATIS corpus. Experiments on Penn treebank sentences of comparable length show an even higher F1 of 71% on nontrivial brackets. We compare distributionally induced and actual part-of-speech tags as input data, and examine extensions to the (...) basic model. We discuss errors made by the system, compare the system to previous models, and discuss upper bounds, lower bounds, and stability for this task. (shrink)

A significant portion of the world’s text is tagged by readers on social bookmarking websites. Credit attribution is an inherent problem in these corpora because most pages have multiple tags, but the tags do not always apply with equal specificity across the whole document. Solving the credit attribution problem requires associating each word in a document with the most appropriate tags and vice versa. This paper introduces Labeled LDA, a topic model that constrains Latent Dirichlet Allocation by defining (...) a one-to-one correspondence between LDA’s latent topics and user tags. This allows Labeled LDA to directly learn word-tag correspondences. We demonstrate Labeled LDA’s improved expressiveness over traditional LDA with visualizations of a corpus of tagged web pages from del.icio.us. Labeled LDA outperforms SVMs by more than 3 to 1 when extracting tag-specific document snippets. As a multi-label text classifier, our model is competitive with a discriminative baseline on a variety of datasets. (shrink)

A* PCFG parsing can dramatically reduce the time required to find the exact Viterbi parse by conservatively estimating outside Viterbi probabilities. We discuss various estimates and give efficient algorithms for computing them. On Penn treebank sentences, our most detailed estimate reduces the total number of edges processed to less than 3% of that required by exhaustive parsing, and even a simpler estimate which can be pre-computed in under a minute still reduces the work by a factor of 5. The algorithm (...) extends the classic A* graph search procedure to a certain hypergraph associated with parsing. Unlike bestfirst and finite-beam methods for achieving this kind of speed-up, the A* parser is guaranteed to return the most likely parse, not just an approximation. The algorithm is also correct for a wide range of parser control strategies and maintains a worst-case cubic time bound. (shrink)

While symbolic parsers can be viewed as deduction systems, this view is less natural for probabilistic parsers. We present a view of parsing as directed hypergraph analysis which naturally covers both symbolic and probabilistic parsing. We illustrate the approach by showing how a dynamic extension of Dijkstra’s algorithm can be used to construct a probabilistic chart parser with an Ç´Ò¿µ time bound for arbitrary PCFGs, while preserving as much of the flexibility of symbolic chart parsers as allowed by the (...) inherent ordering of probabilistic dependencies. (shrink)

This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems — history-based generative parsing models. We report experimental results showing that memory-based learning outperforms many commonly used methods for this task (Witten-Bell, Jelinek-Mercer with fixed weights, decision trees, and log-linear models). However, we can connect these results with the commonly used general class of deleted interpolation models by showing that certain types of memory-based learning, including (...) the kind that performed so well in our experiments, are instances of this class. In addition, we illustrate the divergences between joint and conditional data likelihood and accuracy performance achieved by such models, suggesting that smoothing based on optimizing accuracy directError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMaply might greatly improve performance. (shrink)

Phrase re-ordering is a well-known obstacle to robust machine translation for language pairs with significantly different word orderings. For Arabic-English, two languages that usually differ in the ordering of subject and verb, the subject and its modifiers must be accurately moved to produce a grammatical translation. This operation requires more than base phrase chunking and often defies current phrase-based statistical decoders. We present a conditional random field sequence classi- fier that detects the full scope of Arabic noun phrase subjects (...) in verb-initial clauses at the Fβ=1 61.3% level, a 5.0% absolute improvement over a statistical parser baseline. We suggest methods for integrating the classifier output with a statistical decoder and present preliminary machine translation results. (shrink)

Determining the semantic role of sentence constituents is a key task in determining sentence meanings lying behind a veneer of variant syntactic expression. We present a model of natural language generation from semantics using the FrameNet semantic role and frame ontology. We train the model using the FrameNet corpus and apply it to the task of automatic semantic role and frame identification, producing results competitive with previous work (about 70% role labeling accuracy). Unlike previous models used for this task, (...) our model does not assume that the frame of a sentence is known, and is able to identify null- instantiated roles, which commonly occur in our corpus and whose identification is crucial to natural language interpretation. (shrink)

Psychology as the behaviorist views it is a purely objective experimental branch of natural science. Its theoretical goal is the prediction and control of behavior. Introspection forms no essential part of its methods, nor is the scientific value of its data dependent upon the readiness with which they lend themselves to interpretation in terms of consciousness. The behaviorist, in his efforts to get a unitary scheme of animal response, recognizes no dividing line between man and brute. The behavior of (...) man, with all of its refinement and complexity, forms only a part of the behaviorist's total scheme of investigation. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:Reviewed by:Dr. Ambedkar and Untouchability: Fighting the Indian Caste SystemChristopher S. QueenDr. Ambedkar and Untouchability: Fighting the Indian Caste System. By Christophe Jaffrelot. New York: Columbia University Press, 2005. xiii + 205 pp.Outside of India, Bhimrao Ramji Ambedkar remains virtually unknown. Everyone knows that Mahatma Gandhi led the fight for Indian independence and that his nonviolent marches inspired Dr. King and the American civil rights movement. Most educated men (...) and women have heard of Nehru and some of the political and literary figures that India has produced in modern times. But few know of the first Untouchable to attend college, who went on to earn advanced degrees in the social sciences and law at Columbia University, the London School of Economics, and Grays Inn, who returned to India in the 1920s to launch a civil rights movement for Untouchables, [End Page 168] who drafted the constitution for the Republic of India as its first law minister, and who led a mass conversion to Buddhism weeks before this death.Dr. B. R. Ambedkar (1891–1956) is venerated by millions of Buddhist and low-caste followers in India today, and at the same time feared by politicians determined to preserve the Hindu caste system he vowed to destroy. Admirers call him Babasaheb Ambedkar or simply Baba, using a traditional term of respect for a guiding elder, and many use the greeting Jai Bhim (“Victory to Bhimrao”) within the Untouchable communities. Ambedkar is portrayed on ubiquitous wall calendars, public statues, and home altars alongside that of the Buddha, wearing a Western suit and tie, with the horn-rimmed glasses and pocket pens of a scholar and diplomat. Although widely regarded as a bodhisattva or Buddhist saint, he is never pictured in the robes of a holy man or entreated in prayer by his devotees. And while most of his campaigns for Untouchable human rights were driven back by the Hindu nationalists, many of the provisions of his path-breaking legislation were eventually adopted after his death. In the intervening decades, amid deepening polarization over his legacy, the state government of Maharashtra has published eighteen volumes of Ambedkar’s collected works and the government of India has bestowed on him its highest civilian honor, the Bharat Ratna.Given the dearth of Western scholarship on Ambedkar’s place in the history of modern India and the emergence of socially engaged Buddhism, I welcome Chris-tophe Jaffrelot’s Dr. Ambedkar and Untouchability: Fighting the Indian Caste System. As a social scientist and director of the Centre d’Études et de Recherches Internatio-nales (CERI) who has published more than a dozen books on South Asian politics, Jaffrelot is well qualified to assess Ambedkar’s life and thought. Drawing on a wide range of materials on the social reform movements of the nineteenth and twentieth centuries and Ambedkar’s contributions to sociology and politics, the author aims to redress Ambedkar’s neglect by Indian scholars before the 1990s, when the low-caste movement began finally to gain traction. However, he does not address the anomaly of Ambedkar’s neglect by all but a small circle of Western authors.1The strength of Dr. Ambedkar and Untouchability is its concise analysis of the geographical, political, and social context of Ambedkar’s career. Jaffrelot shows how British recruitment of the Mahars, members of Ambedkar’s lowly but numerous caste, for service in the colonial army resulted in disproportionate levels of literacy. Ambedkar was the fourteenth child in such a military family, whose father held the rank of major and served as a school master for the barracks. Both parents and all of Bhimrao’s uncles could read and write, compared to less than one percent of Mahars in village life. Moreover, in spite of his brilliance and determination, Ambedkar could not have continued his education without the financial support of Maratha maharajahs who opposed the Brahmins’ monopoly in education. “Ambedkar was the heir to a regional tradition; his struggle harked back to the anti-Brahmin movements which emerged in western Maharashtra from the mid-nineteenth century onward, a precocity that only the Dravidian South—the other key area of anti-Brahmin mobilization—could match.”Jaffrelot presents... (shrink)

In lieu of an abstract, here is a brief excerpt of the content:Collective Violence, Sacrifice, and Conflict Resolution in the Works of Paul Claudel Christopher G. Flood University ofSurrey, England Claudel's career as a writer spanned almost seventy years, from the 1880s to the 1950s. The publication of his collected works now runs to twenty-nine large volumes, excluding his correspondence and diaries, so a brief overview of any particular dimension of his writing must necessarily be reductive. On the other (...) hand, Claudel's work lends itself particularly well to discussion in terms of the relationship between violence, sacrifice and religion. In a valuable study published more than twenty years ago under the title, Claudel et l'usurpateur, Jacques Petit drew attention to the recurrence in Claudel's plays, and in many of his non- fictional writings, of a narrative structure hinging on acts of usurpation and counter-usurpation. There is a pattern of conflictual rivalry, domination and coercion, whereby acts of aggression are ultimately legitimized, or in some sense excused, in the light of a positive outcome, providential necessity and/or reconciliation between usurper and victim. Claudel's world is indeed "a world of violence," as Petit puts it (79, ch. title).1 It is also a world ofreligion: after his return to the Catholic Church in 1890, all of Claudel's major dramatic works intermesh the process of usurpation with themes deriving from his religious beliefs, and the same is true of many of his non-fictional writings. My aim is not to reinvent the wheel by going back over all of the terrain mapped out by Petit. Nor do I intend to rework Petit's empirical model wholesale in the light of René Girard's anthropological model of mimetic desire and sacrificial violence, although there are obvious areas of convergence between them. However, I shall draw implicitly on both, in order to Translations throughout this paper are my own. 160Christopher G. Flood argue that the notion of sacrifice, which is central to the resolution of rivalries in Claudel's major plays, is transformed into an idiosyncratic conception of international conflict resolution in various non-fictional writings which emerge from his forty years of experience in his parallel career as a profes sional diplomat.2 1 shall start with a schematic discussion of certain features of the plays. The first point relates to Claudel's assumptions concerning the mechanisms involved in the outbreak of individual or collective violence. It needs to be emphasized that in his plays the path towards violence is always opened by a withdrawal or weakening of temporal and/or spiritual authority. This allows the crystallization, and the direct expression, of latent rivalries which eventually lead to an explosion of aggression. The causes of the violence invariably center on the fact that one individual or group is in possession of an object which is coveted by another individual or group. The question of whether Claudel himself appears to recognize a mimetic element in this pattern of behavior would be too complex, and too fraught with imponderables, to discuss here, but there are some indications that he does so. Whatever the case, in the absence of authority, rivalry and jealousy engender verbal, and usually physical conflict, culminating in usurpation of the desired object. Thus, for example, in Tête d'or, the elderly Emperor of the unnamed kingdom has neither the authority nor the resolution to defend his kingdom against external invasion, or against the man who saves the kingdom only to usurp the throne and murder the Emperor himself.3 Similarly, in the second version of La Ville, neither Besme, the positivistic scientist and plutocrat who has created the godless City, nor his brother Lambert, the former politician, has the will to maintain or defend the society against the tensions emerging within it. Thus, the City dissolves first into immobility, then revolution. Or again, in the family drama of La Jeune Fille Violaine (second version), the obsessional rage andjealousy ofMara towards her elder sister, Violaine, explodes into coercion, slander, and horrific violence when their father absents himself from the farm for an indefinite period, leaving Violaine to marry Jacques Hury: the fact that Hury loves Violaine, but does not love Mara, makes the latter all the... (shrink)

Par rapport à la problématique de la théodicée classique, l'article opère un renversement de perspective en s'interrogeant sur les forces dont dispose l'humanité dans son combat spirituel contre le mal. L'argument se développe en quatre parties. Une première circonscrit le terrain du questionnement en rappelant comment on y a accédé dans l'histoire de la pensée, et surtout, comment l'expérience du mal-malheur a suscité des ressources trop souvent cachées par une conception du combat spirituel, unilatéralement ­ aux prises avec le mal (...) moral et le péché. Une deuxième partie se situe au niveau des formes de résistance communes aux différents courants religieux ou spirituels de l'humanité. L'approche herméneutique permet de les aborder dans un esprit « oecuménique », approprié à la perspective d'une résistance commune au mal, ce qui fait émerger la question de 1'ultime profondeur de nos ressources spirituelles. C'est sur cet arrière-fond qu'on pourra penser, dans un troisième temps, la concep­tion chrétienne de la résistance au mal comme une manière de donner existence à Dieu au sein de nos combats. La dernière partie devra s'affronter à la ténacité d'une souffrance irréductible, liée à l'existence même de l'homme, que seule l'attitude de l'abandon parvient à intégrer dans la visée théologale de la béatitude.In relation to the field of inquiry concerning classical theodicy, this article reverses the perspective in questioning the forces that humanity disposes of in its spiritual combat against evil. The argument is developed in four parts. The first part limits the question by recalling how one approaches it in the history of ideas and, especially, how the experience of evil-misfortunes resurrected sources that were too often hidden by a concept of spiritual combat unilaterally at grips with moral evil and sin. The second part is concerned with the forms of common resistances to the different religious or spiritual currents of humanity. A hermeneutical approach allows one to begin in an « ecumenical » attitude, appropriate to the perspective of a common resistance to evil, which brings up the question of the ultimate depth of our spiritual resources. It is with this background that one could think of, on the third level, the Christian conception of resistance to evil as a way of giving existence to God in the middle of our combats. The last Part confronts the tenacity of an irreducible suffering, tied in to man's very existence, which only the attitude of abandonment succeeds in integrating into the theological perspective of beatitude. (shrink)

Cet essai se propose de retracer le parcours de John Milton, formidable poète, mais aussi prosateur au service de la cause républicaine dans l’Angleterre révolutionnaire des années 1640-1660. On y découvre un penseur radical contrarié, figure puritaine s’il en faut, mais également un écrivain doué d’un humanisme profond. Ces tensions créatrices l’amènent à réconcilier, d’une manière peu banale, l’homme avec Dieu pour poser la liberté, qu’elle soit personnelle, domestique ou politique. This essay purports to show the life and works of (...) John Milton, universally known as a brilliant poet, but we should also remember him as an unequalled pamphleteer defending the republican cause in revolutionary England 1640-1660. There we discover a thwarted radical thinker, caught between humanism and Puritanism. Yet Milton eventually manages to reconcile God’s sovereignty with man’s liberty in quite an original way as he asserts freedom in all fields. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:“Something Breaks Through a Little”: The Marriage of Zen and Sophia in the Life of Thomas MertonChristopher PramukThe fact that you are a Zen Buddhist and I am a Christian monk, far from separating us, makes us most like one another. How many centuries is it going to take for people to discover this fact? 1Though Merton’s “turn to the East” began well before Vatican II would turn the (...) eyes of Roman Catholics toward the ecumenical and non-Christian world, its fruits would not generally appear in published form until after the Council. In works such as Mystics and Zen Masters (1967) and Zen and the Birds of Appetite (1968), Merton spends much labor correcting caricatures of Eastern spirituality prominent in the West, especially in the American counterculture. These remain vital texts today because they give us the mature Merton at his best, pressed to the limit of discursive communication on vexatious systematic and epistemological problems—and this after more than a decade of reflection and growth with respect to interfaith dialogue. Indeed, brilliantly realized essays such as “The New Consciousness” and “A Christian Looks at Zen” reveal Merton to be much more “conservative” than conservative caricatures make him out to be, and much more “liberal” than most progressives. Merton writes with the authority of a committed Christian immersed in serious dialogue, with all its challenges and risks, and not just as one who talks about it.Few serious students of Merton’s life and writings—whether inspired by his universal scope of vision or scandalized by it—would dispute that his conception of the divine changed as he allowed deeper encounters with Eastern traditions to interrogate his faith. What is less commonly understood, however, is how closely Merton’s engagement with Zen corresponded with his internalization of a deep thread in the Christian East, namely, the Sophia tradition of Russian Orthodoxy, or “sophiology” as known in its speculative form, associated with thinkers such as Vladimir Soloviev (d. 1900), Sergius Bulgakov (d. 1944), and Paul Evdokimov (d. 1970). What attracted Merton to these thinkers was their recasting of the Christian narrative of salvation in the boldest imaginative and metaphysical terms; from biblical, patristic, and modern philosophical sources they had fashioned a “positive theology,” a theology brimming with content. Though Merton himself would never develop a formal [End Page 67] sophiology, his internalization of Russian imagery is amply evidenced in journals, letters, notes, and in seminal works such as The Behavior of Titans (1961), The New Man (1961), and New Seeds of Contemplation (1961). The prose poem Hagia Sophia (1962), still one of Merton’s most understudied and “secret” works, is by far the most realized, lyrical, and daring of his meditations on the Wisdom figure of Sophia.In this article I wish to suggest that the striking “coincidence” of Zen and Sophia in Merton’s life during the late 1950s was not merely a coincidence, but hinged in part on epistemological difficulties he was wrestling with in the midst of radically shifting cultural, ecclesial, and political horizons. While in one sense the irruption of Sophia into Merton’s consciousness in the late 1950s was just one thread woven into the larger mosaic of his “turn to the world,” it was, I believe, the golden thread that helped him to hold the fabric together, ever more centered in Christ. In other words, this “bringing together” of apparent opposites does not end with epistemology. What emerges in Merton’s concurrent study of Zen and Russian sophiology is a kind of “story-shaped” Christology, a story told through the life of Merton but haunted more and more by the mysterious figure of Sophia.2Nondualism: A Zen and Ancient Christian “Way of Seeing”In a letter dated March 12, 1959, Merton introduced himself to Zen scholar D. T. Suzuki, then known worldwide for his gift for translating the teachings of Zen Buddhism to the West.3 After receiving a warm reply and some poems from Suzuki, Merton wrote a second letter. His tone is warm and forthright, written as one might address a respected mentor or a long-time friend. What is most striking is the intimacy with which... (shrink)

Comment transmettre et diffuser les vérités révélées sans recourir à une imagination poétique ou artistique, suspecte de rabattre l'homme vers les séductions terrestres et de le gonfler d'orgueil? La solution fournie par Jean - François Pic de la Mirándole à ce problème dans son De Imaginatione consacre l'émergence d'une fonction nouvelle de l'imagination, que l'on verra reprise et développée dans les grands textes apologétiques du XVIIe siècle. How can one pass on and spread revealed truths without resort to a poetic (...) or artistic imagination, suspect of humbling man towards terrestrial seductions, hence inflating him with pride? The solution offered by Giovanni Francesco Pico della Mirándola to this problem in his De Imaginatione sanctions the surge of a new function of imagination which will be seen caught up again and developed in the great apologetic texts of the XVIIth century. (shrink)

1 Boolean retrieval 1 2 The term vocabulary and postings lists 19 3 Dictionaries and tolerant retrieval 49 4 Index construction 67 5 Index compression 85 6 Scoring, term weighting and the vector space model 109 7 Computing scores in a complete search system 135 8 Evaluation in information retrieval 151 9 Relevance feedback and query expansion 177 10 XML retrieval 195 11 Probabilistic information retrieval 219 12 Language models for information retrieval 237 13 Text classification and Naive Bayes 253 (...) 14 Vector space classification 289 15 Support vector machines and machine learning on documents 319 16 Flat clustering 349 17 Hierarchical clustering 377 18 Matrix decompositions and latent semantic indexing 403 19 Web search basics 421 20 Web crawling and indexes 443 21 Link analysis 461.. (shrink)

We propose a model of natural language inference which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. We extend past work in natural logic, which has focused on semantic containment and monotonicity, by incorporating both semantic exclusion and implicativity. Our model decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical semantic relation for each edit; propagates these relations upward through a semantic composition tree according to properties of (...) intermediate nodes; and joins the resulting semantic relations across the edit sequence. A computational implementation of the model achieves 70% accuracy and 89% precision on the FraCaS test suite. Moreover, including this model as a component in an existing system yields significant performance gains on the Recognizing Textual Entailment challenge. (shrink)

This paper proposes a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering and textual entailment have approximated the entailment problem as that of computing the best alignment of the hypothesis to the text, using a locally decomposable matching score. While this formulation is adequate for representing local (word-level) phenomena such as synonymy, it is incapable of representing global interactions, such as that between verb negation (...) and the addition/removal of qualifiers, which are often critical for determining entailment. We propose a pipelined approach where alignment is followed by a classification step, in which we extract features representing high-level characteristics of the entailment problem, and give the resulting feature vector to a statistical classifier trained on development data. (shrink)

We present a system for deciding whether a given sentence can be inferred from text. Each sentence is represented as a directed graph (extracted from a dependency parser) in which the nodes represent words or phrases, and the links represent syntactic and semantic relationships. We develop a learned graph matching model to approximate entailment by the amount of the sentence’s semantic content which is contained in the text. We present results on the Recognizing Textual Entailment dataset (Dagan et al., 2005), (...) and show that our approach outperforms Bag- Of-Words and TF-IDF models. (shrink)

Pendant presque deux millénaires, la toute‑puissance a été un attribut inséparable de Dieu et de la foi en Dieu. Depuis un certain temps, et en particulier au xxe siècle, cette toute‑puissance est contestée aussi bien depuis l’extérieur que depuis l’intérieur de la théologie. À l’intérieur de la théologie, on lui substitue volontiers une impuissance que Dieu assumerait délibérément. La question est de savoir si l’affirmation et la négation de cet attribut ne relèvent pas du même type de discours ; d’un (...) discours qui se prétend capable de savoir, d’affirmer, de contester, de dominer, de régler...Quel est ici le statut de l’homme et du langage humain? Face à la « problématique » de la toute‑puissance de Dieu, l’homme dispose‑t‑il encore de ses points de repère, de ses mots, de ses certitudes?For almost two millennia, omnipotence has been an attribute of God inseparable from faith in God. Recently, and in particular since the twentieth century, the notion of divine omnipotence has been contested from outside the field of theology as well as from within. Some theologians have preferred to substitute for omnipotence a notion of powerlessness deliberately assumed by God. One might question however whether either the affirmation or the denial of omnipotence do not arise from the same type of discourse: a discourse that claims the ability to know, to assert, to question, to dominate, to rule...What then can be said here of the status of man and of human language? Confronted with the issue of God’s omnipotence, what remains to man as points of reference, what is left of his words, his certitudes? (shrink)

I examine what would be necessary to move part-of-speech tagging performance from its current level of about 97.3% token accuracy (56% sentence accuracy) to close to 100% accuracy. I suggest that it must still be possible to greatly increase tagging performance and examine some useful improvements that have recently been made to the Stanford Part-of-Speech Tagger. However, an error analysis of some of the remaining errors suggests that there is limited further mileage to be had either from better machine learning (...) or better features in a discriminative sequence classifier. The prospects for further gains from semisupervised learning also seem quite limited. Rather, I suggest and begin to demonstrate that the largest opportunity for further progress comes from improving the taxonomic basis of the linguistic resources from which taggers are trained. That is, from improved descriptive linguistics. However, I conclude by suggesting that there are also limits to this process. The status of some words may not be able to be adequately captured by assigning them to one of a small number of categories. While conventions can be used in such cases to improve tagging consistency, they lack a strong linguistic basis. (shrink)

This paper presents a new method for producing a dictionary of subcategorization frames from unlabelled text corpora. It is shown that statistical filtering of the results of a finite state parser running on the output of a stochastic tagger produces high quality results, despite the error rates of the tagger and the parser. Further, it is argued that this method can be used to learn all subcategorization frames, whereas previous methods are not extensible to a general solution to the problem.

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming parsers have restricted training and evaluation to artificially short sentences, we present the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data. Our efficiency is primarily due to the use of stochastic optimization techniques, as well as parallelization and chart prefiltering. On WSJ15, (...) we attain a state-of-the-art F-score of 90.9%, a 14% relative reduction in error over previous models, while being two orders of magnitude faster. On sentences of length 40, our system achieves an F-score of 89.0%, a 36% relative reduction in error over a generative baseline. (shrink)

The correct locus (or loci) of binding theory has been a matter of much discussion. Theories can be seen as varying along at least two dimensions. The rst is whether binding theory is con gurationally determined (that is, the theory exploits the geometry of a phrase marker, appealing to such purely structural notions as c-command and government) or whether the theory depends rather on examining the relations between items selected by a predicate (where by selection I am intending to cover (...) everything from semantic dependencies to syntactic subcategorization). The second is the level of grammar on which binding is de ned. Attempting to roughly equate levels across di erent theories, suggestions have included the semantics/lexical conceptual structure (Jackendo 1992), thematic structure (Jackendo 1972, Wilkins 1988), argument structure/D-structure/initial grammatical relations (Manning 1994, Belletti and Rizzi 1988, Perlmutter 1984), surface syntax/grammatical relations, logical form, linear order, pragmatics (Levinson 1991), and discourse (Iida 1992). The data is su ciently varied and complex that many theories end up as mixtures, variously employing a combination of elements along both dimensions (for instance, Chomsky (1986) relies purely on con gurational notions for the relationship between an anaphor and its antecedent, but uses concepts from selection in the de nition of the binding domain of an anaphor). LFG has always rejected a con gurational account of binding. For instancError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMapError: Illegal entry in bfrange block in ToUnicode CMape, Simpson (1991) argues that a con gurational theory of binding in Warlpiri cannot be maintained, among other reasons because nite clauses lack a VP.. (shrink)

The alignment problem—establishing links between corresponding phrases in two related sentences—is as important in natural language inference (NLI) as it is in machine translation (MT). But the tools and techniques of MT alignment do not readily transfer to NLI, where one cannot assume semantic equivalence, and for which large volumes of bitext are lacking. We present a new NLI aligner, the MANLI system, designed to address these challenges. It uses a phrase-based alignment representation, exploits external lexical resources, and capitalizes on (...) a new set of supervised training data. We compare the performance of MANLI to existing NLI and MT aligners on an NLI alignment task over the well-known Recognizing Textual Entailment data. We show that MANLI significantly outperforms existing aligners, achieving gains of 6.2% in F1 over a representative NLI aligner and 10.5% over GIZA++. (shrink)

Linking constructions involving dሇ (DE) are ubiquitous in Chinese, and can be translated into English in many different ways. This is a major source of machine translation error, even when syntaxsensitive translation models are used. This paper explores how getting more information about the syntactic, semantic, and discourse context of uses of dሇ (DE) can facilitate producing an appropriate English translation strategy. We describe a finergrained classification of dሇ (DE) constructions in Chinese NPs, construct a corpus of annotated examples, and (...) then train a log-linear classifier, which contains linguistically inspired features. We use the DE classifier to preprocess MT data by explicitly labeling dሇ (DE) constructions, as well as reordering phrases, and show that our approach provides significant BLEU point gains on MT02 (+1.24), MT03 (+0.88) and MT05 (+1.49) on a phrasedbased system. The improvement persists when a hierarchical reordering model is applied. (shrink)

Abeill´e and Godard (1994) seek to show that the rightward branching analysis of French tense auxiliaries shown in (1b), that I argued for in Manning (1992) and which is widely adopted in general, is wrong, and that rather we should adopt a flat analysis for this construction as shown in (1c), and they show how such an analysis can be realized within HPSG (Pollard and Sag 1994).

Technology for local textual inference is central to producing a next generation of intelligent yet robust human language processing systems. One can think of it as Information Retrieval++. It is needed for a search on male fertility may be affected by use of cell phones to match a document saying Startling new research into mobile phones suggests they can reduce a man’s sperm count up to 30%, despite the fact that the only word overlap is phones. But textual inference is (...) useful more broadly. It is an enabling technology for applications of document interpretation, such as customer response management, where one would like to conclude from the message My Squeezebox regularly skips during music playback that Sender has set up Squeezebox and Sender can hear music through Squeezebox, and information extraction, where from the text Jorma Ollila joined Nokia in 1985 and held a variety of key management positions before taking the helm in 1992, one wants to extract that Jorma Ollila has served as the CEO of Nokia, a relation that might be more formally denoted as role(CEO, Nokia, Jorma Ollila). Textual inference is a difficult problem (as the results from early evaluations have shown): current systems do statistically better than random guessing, but not by very much. Nevertheless, it is also an area where there is promising developing technology and a good deal of natural language community interest. In other words, it is an ideal research problem. To further this research agenda, data sets have been constructed to assess textual inference systems. This paper examines how the task of textual inference has been and should be defined and discusses what kind of evaluation data is appropriate for the task.1.. (shrink)

This paper shows that a simple two-stage approach to handle non-local dependencies in Named Entity Recognition (NER) can outperform existing approaches that handle non-local dependencies, while being much more computationally efficient. NER systems typically use sequence models for tractable inference, but this makes them unable to capture the long distance structure present in text. We use a Conbel.

This paper examines feature selection for log linear models over rich constraint-based grammar (HPSG) representations by building decision trees over features in corresponding probabilistic context free grammars (PCFGs). We show that single decision trees do not make optimal use of the available information; constructed ensembles of decision trees based on different feature subspaces show signifi- cant performance gains (14% parse selection error reduction). We compare the performance of the learned PCFG grammars and log linear models over the same features.

Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the sparseness of counts of such dependencies, smoothing and the ability to use multiple sources of knowledge are important challenges. For example, if the probability P(N |V ) of noun N being the subject of verb V is high, and V takes similar objects to V , and V is synonymous to V , then (...) we want to conclude that P(N |V ) should also be reasonably high—even when those words did not cooccur in the training data. (shrink)

This report details experimental results of using stochastic disambiguation models for parsing sentences from the Redwoods treebank (Oepen et al., 2002). The goals of this paper are two-fold: (i) to report accuracy results on the more highly ambiguous latest version of the treebank, as compared to already published results achieved by the same stochastic models on a previous version of the corpus, and (ii) to present some newly developed models using features from the HPSG signs, as well as the MRS (...) dependency graphs. (shrink)

This paper examines the Stanford typed dependencies representation, which was designed to provide a straightforward description of grammatical relations for any user who could benefit from automatic text understanding. For such purposes, we argue that dependency schemes must follow a simple design and provide semantically contentful information, as well as offer an automatic procedure to extract the relations. We consider the underlying design principles of the Stanford scheme from this perspective, and compare it to the GR and PARC representations. Finally, (...) we address the question of the suitability of the Stanford scheme for parser evaluation. (shrink)

Sustained attention, a key cognitive skill that improves during childhood and adolescence, tends to be worse in some emotional and behavioural disorders. Sustained attention is typically studied in non-affective task contexts; here, we used a novel task to index performance in affective versus neutral contexts across adolescence (N = 465; ages 11–18). We asked whether: (i) performance would be worse in negative versus neutral task contexts; (ii) performance would improve with age; (iii) affective interference would be greater in younger (...) adolescents; (iv) adolescents at risk for depression and higher in anxiety would show overall worse performance; and (v) would show differential performance in negative contexts. Results indicated that participants performed more poorly in negative contexts and showed age-related performance improvements. Those at risk of depression performed more poorly than those at lower risk. However, there was no difference between groups as a result of affective context. For anxiety there was no difference in performance as a function of severity. However, those with higher anxiety showed less variance in their reaction times to negative stimuli than those with lower anxiety. One interpretation is that moderate levels of emotional arousal associated with anxiety make individuals less susceptible to the distracting effects of negative stimuli. (shrink)

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar. Indeed, its performance of 86.36% (LP/LR F1) is better than that of early lexicalized PCFG models, and surprisingly close to the current state-of-theart. This result has potential uses beyond establishing a strong lower bound on the maximum possible accuracy of unlexicalized models: an unlexicalized PCFG is (...) much more compact, easier to replicate, and easier to interpret than more complex lexical models, and the parsing algorithms are simpler, more widely understood, of lower asymptotic complexity, and easier to optimize. (shrink)