Articles

Almost all automatic semantic role label- ing (SRL) systems rely on a preliminary parsing step that derives a syntactic struc- ture from the sentence being analyzed. This makes the choice of syntactic repre- sentation an essential design decision. In this paper, we study the influence of syn- tactic representation on …...

To realize high quality machine transla- tion, we proposed a Non-Compositional Language Model, and developed a sen- tence pattern dictionary of 226,800 pat- tern pairs for Japanese compound and complex sentences consisting of 2 or 3 clauses. In pattern generation from a par- allel corpus, Compositional Constituents that could be …...

As Chinese text is written without word boundaries, effectively recognizing Chi- nese words is like recognizing colloca- tions in English, substituting characters for words and words for collocations. However, existing topical models that in- volve collocations have a common limi- tation. Instead of directly assigning a top- ic to a …...

In this paper, we introduce a new frame- work for recognizing textual entailment (RTE) which depends on extraction of the set of publicly-held beliefs – known as dis- course commitments – that can be ascribed to the author of a text (t) or a hypothesis (h). We show that once …...

This paper explores the relationship be- tween various measures of unsupervised part-of-speech tag induction and the per- formance of both supervised and unsuper- vised parsing models trained on induced tags. We find that no standard tagging metrics correlate well with unsupervised parsing performance, and several metrics grounded in information theory …...

This paper proposes a novel lexicalized ap- proach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) mod- els which combine rich context informa- tion for selecting translation rules dur- ing decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT …...

We introduce a technique for analyzing the temporal evolution of the salience of par- ticipants in a discussion. Our method can dynamically track how the relative impor- tance of speakers evolve over time using graph based techniques. Speaker salience is computed based on the eigenvector cen- trality in a graph …...

This paper explores the use of the homo- topy method for training a semi-supervised Hidden Markov Model (HMM) used for sequence labeling. We provide a novel polynomial-time algorithm to trace the lo- cal maximum of the likelihood function for HMMs from full weight on the la- beled data to full …...

We present dependency-based n-gram models for general-purpose, wide- coverage, probabilistic sentence realisa- tion. Our method linearises unordered dependencies in input representations directly rather than via the application of grammar rules, as in traditional chart- based generators. The method is simple, efficient, and achieves competitive accu- racy and complete coverage on …...

The paper offers a new type of approach to the semantic phenomenon of adverbial aspect shift within the framework of finite- state temporal semantics. The heart of the proposal is a supervaluational concept of underspecification, and the idea of treat- ing the meanings of temporal prepositions as dynamic presuppositions. The …...

Semantic relatedness between words is important to many NLP tasks, and nu- merous measures exist which use a vari- ety of resources. Thus far, such work is confined to measuring similarity between two words (or two texts), and only a handful utilize the web as a corpus. This paper introduces …...

The use of topical features is abundant in Natural Language Processing (NLP), a major example being in dictionary-based Word Sense Disambiguation (WSD). Yet previous research does not attempt to measure the level of topic cohesion in documents, despite assertions of its ef- fects. This paper introduces a quantitative measure of …...

We present an approach to ontology popu- lation based on a lexical substitution tech- nique. It consists in estimating the plausi- bility of sentences where the named entity to be classified is substituted with the ones contained in the training data, in our case, a partially populated ontology. Plausibility is …...

This paper presents a probabilistic model for resolution of non-pronominal anaphora in biomedical texts. The model seeks to find the antecedents of anaphoric expres- sions, both coreferent and associative ones, and also to identify discourse-new expres- sions. We consider only the noun phrases referring to biomedical entities. The model reaches …...

In contrast to LFG and HPSG, there is to date no large scale Tree Adjoining Gram- mar (TAG) equiped with a compositional semantics. In this paper, we report on the integration of a unification-based se- mantics into a Feature-Based Lexicalised TAG for French consisting of around 6 000 trees. We …...

This paper studies sentiment analysis from the user-generated content on the Web. In particular, it focuses on mining opinions from comparative sentences, i.e., to determine which entities in a compari- son are preferred by its author. A typical comparative sentence compares two or more entities. For example, the sentence, “the …...

This paper presents a method of retriev- ing bilingual collocations of a verb and its objective noun from cross-lingual docu- ments with similar contents. Relevant doc- uments are obtained by integrating cross- language hierarchies. The results showed a 15.1% improvement over the baseline non- hierarchy model, and a 6.0% improvement …...

The most critical issue in generating and recognizing paraphrases is development of wide-coverage paraphrase knowledge. Previous work on paraphrase acquisition has collected lexicalized pairs of expres- sions; however, the results do not ensure full coverage of the various paraphrase phenomena. This paper focuses on pro- ductive paraphrases realized by general …...

This paper provides a parsing algorithm for the Lambek calculus which is polyno- mial time for a more general fragment of the Lambek calculus than any previously known algorithm. The algorithm runs in worst-case time O(n5) when restricted to a certain fragment of the Lambek calcu- lus which is motivated …...

We present a novel approach to word reordering which successfully integrates syntactic structural knowledge with phrase-based SMT. This is done by con- structing a lattice of alternatives based on automatically learned probabilistic syntactic rules. In decoding, the alter- natives are scored based on the output word order, not the order …...