Articles

Identifying textual inferences, where the meaning of one text follows from another, is a general underlying task within many natu- ral language applications. Commonly, it is ap- proached either by generative syntactic-based methods or by “lightweight” heuristic lexical models. We suggest a model which is confined to simple lexical information, …...

Previous work on paraphrase extraction and application has relied on either parallel datasets, or on distributional similarity met- rics over large text corpora. Our approach combines these two orthogonal sources of in- formation and directly integrates them into our paraphrasing system’s log-linear model. We compare different distributional similar- ity feature-sets …...

Discourse coherence is an important aspect of natural language that is still understudied in computational linguistics. Our aim is to learn factors that constitute coherent discourse from data, with a focus on how to realize predicate- argument structures (PAS) in a model that ex- ceeds the sentence level. In particular, …...

We present a novel technique for jointly predict- ing semantic arguments for lexical predicates. The task is to find the best matching between seman- tic roles and sentential spans, subject to struc- tural constraints that come from expert linguistic knowledge (e.g., in the FrameNet lexicon). We formulate this task as …...

We present an ensemble-based framework for semantic lexicon induction that incorpo- rates three diverse approaches for semantic class identification. Our architecture brings together previous bootstrapping methods for pattern-based semantic lexicon induction and contextual semantic tagging, and incorpo- rates a novel approach for inducing semantic classes from coreference chains. The three …...

Word Sense Disambiguation aims to label the sense of a word that best applies in a given context. Graded word sense disambiguation relaxes the single label assumption, allow- ing for multiple sense labels with varying de- grees of applicability. Training multi-label classifiers for such a task requires substan- tial amounts …...

This paper describes Bayesian selectional preference models that incorporate knowledge from a lexical hierarchy such as WordNet. In- spired by previous work on modelling with WordNet, these approaches are based either on “cutting” the hierarchy at an appropriate level of generalisation or on a “walking” model that selects a path …...

We present a method for learning syntax- semantics mappings for verbs from unanno- tated corpora. We learn linkings, i.e., map- pings from the syntactic arguments and ad- juncts of a verb to its semantic roles. By learn- ing such linkings, we do not need to model in- dividual semantic roles …...

Many types of polysemy are not word specific, but are instances of general sense alternations such as ANIMAL-FOOD. Despite their perva- siveness, regular alternations have been mostly ignored in empirical computational semantics. This paper presents (a) a general framework which grounds sense alternations in corpus data, generalizes them above individual …...

We present a rule-based method to automati- cally create a large-coverage semantic lexicon of French adjectives by extracting paradig- matic relations from lexicographic definitions. Formalized adjectival resources are, indeed, scarce for French and they mostly focus on morphological and syntactic information. Our objective is, therefore, to contribute enriching the available …...

Over the past decade, several underspec- ification frameworks have been proposed that efficiently solve a big subset of scope- underspecified semantic representations within the realm of the most popular constraint-based formalisms. However, there exists a family of coherent natural language sentences whose underspecified representa- tion does not belong to this …...

We propose an unsupervised system that learns continuous degrees of lexicality for noun-noun compounds, beating a strong base- line on several tasks. We demonstrate that the distributional representations of compounds and their parts can be used to learn a fine- grained representation of semantic contribu- tion. Finally, we argue such …...

This paper complements a series of works on implicative verbs such as manage to and fail to. It extends the description of simple im- plicative verbs to phrasal implicatives as take the time to and waste the chance to. It shows that the implicative signatures of over 300 verb-noun collocations …...

Neurosemantics aims to learn the mapping between concepts and the neural activity which they elicit during neuroimaging ex- periments. Different approaches have been used to represent individual concepts, but current state-of-the-art techniques require extensive manual intervention to scale to arbitrary words and domains. To over- come this challenge, we initiate …...

Modeling user preferences is crucial in many real-life problems, ranging from individual and collective decision-making to strategic in- teractions between agents and game theory. Since agents do not come with their prefer- ences transparently given in advance, we have only two means to determine what they are if we wish …...

We study the task of automatically disam- biguating word combinations such as jump the gun which are ambiguous between a lit- eral and MWE interpretation, focusing on the utility of type-level features from an MWE lexicon for the disambiguation task. To this end we combine gold-standard idiomatic- ity of tokens …...

Semantic role classification accuracy for most languages other than English is constrained by the small amount of annotated data. In this pa- per, we demonstrate how the frame-to-frame relations described in the FrameNet ontology can be used to improve the performance of a FrameNet-based semantic role classifier for Swedish, a …...

We present a framework, based on Sejane and Eger (2012), for inducing lexical semantic ty- pologies for groups of languages. Our frame- work rests on lexical semantic association net- works derived from encoding, via bilingual corpora, each language in a common reference language, the tertium comparationis, so that distances between …...

Given a set of images with related captions, our goal is to show how visual features can improve the accuracy of unsupervised word sense disambiguation when the textual con- text is very small, as this sort of data is com- mon in news and social media. We extend previous work …...

We report ongoing work on the development of agents that can implicitly coordinate with their partners in referential tasks, taking as a case study colour terms. We describe algo- rithms for generation and resolution of colour descriptions and report results of experiments on how humans use colour terms for reference …...