Manual development of large subcategorised lexicons has proved difficult because predicates change behaviour between sublanguages, domains and over time. Yet access to a comprehensive subcategorization lexicon is vital for successful parsing capable of recovering predicate-argument relations, and probabilistic parsers would greatly benefit from accurate information concerning the relative likelihood of different subcategorisation frames (scfs) of a given predicate. Acquisition of subcategorization lexicons from textual corpora has recently become increasingly popular. Although this work has met with some success, resulting lexicons indicate a need for greater accuracy. One significant source of error lies in the statistical filtering used for hypothesis selection, i.e. for removing noise from automatically acquired scfs. This thesis builds on earlier work in verbal subcategorization acquisition, taking as a starting point the problem with statistical filtering. Our investigation shows that statistical filters tend to work poorly because not only is the underlying distribution zipfian, but there is also very little correlation between conditional distribution of

Selecting the most appropriate sense for an ambiguous word in a sentence is a central problem in Natural Language Processing. In this paper, we present a method that attempts to disambiguate all the nouns, verbs, adverbs and adjectives in a text, using the senses pro- vided in WordNet. The senses are ranked us- ing two sources of information: (1) the Inter- net for gathering statistics for word-word co- occurrences and (2)'WordNet for measuring the semantic density for a pair of words. We report an average accuracy of 80% for the first ranked sense, and 91% for the first two ranked senses. Extensions of this method for larger windows of more than two words are considered.

We present an unsupervised method for word sense disambiguation that exploits translation correspondences in parallel corpora. The technique takes advantage of the fact that crosslanguage lexicalizations of the same concept tend to be consistent, preserving some core element of its semantics, and yet also variable, reflecting differing translator preferences and the influence of context. Working with parallel corpora introduces an extra complication for evaluation, since it is difficult to find a corpus that is both sense tagged and parallel with another language; therefore we use pseudotranslations, created by machine translation systems, in order to make possible the evaluation of the approach against a standard test set. The results demonstrate that word-level translation correspondences are a valuable source of information for sense disambiguation.

Verbs were clustered semantically on the basis of their alternation behariota', as characterised by l,heir synl,acLi(: subcaLegorisation lYame, s exLra(:Lcd from maximran proba,biliLy 1)arses ()[ a robttsL sl,adsLical 1)arsel ', ;red (:Oml)let,ed by assignin/5 WordNet, classes as select, ional preth'enees t,o t, he fi'ame argumenLs. The clustering was achieved (a.) iLeratively by mea.- sm'ing Lhe relal;ive ent,ropy bet,ween t.he verbs' ability (lisl.ribut, ions over the frame tyl)cS, and (b) l)y ul,ilising a latenl, class mm.lysis based on the joint fi'eqmm(:ies of verbs and frame types.

Selectional preference learning methods have usually focused on wordto -class relations, e.g., a verb selects as its subject a given nominal class. This papers extends previous statistical models to class-to-class preferences, and presents a model that learns selectional preferences for classes of verbs. The motivation is twofold: different senses of a verb may have different preferences, and some classes of verbs can share preferences. The model is tested on a word sense disambiguation task which uses subject-verb and object-verb relationships extracted from a small sense-disambiguated corpus. 1

The computation of selectional preferences, the admissible argument values for a relation, is a well-known NLP task with broad applicability. We present LDA-SP, which utilizes LinkLDA (Erosheva et al., 2004) to model selectional preferences. By simultaneously inferring latent topics and topic distributions over relations, LDA-SP combines the benefits of previous approaches: like traditional classbased approaches, it produces humaninterpretable classes describing each relation’s preferences, but it is competitive with non-class-based methods in predictive power. We compare LDA-SP to several state-ofthe-art methods achieving an 85 % increase in recall at 0.9 precision over mutual information (Erk, 2007). We also evaluate LDA-SP’s effectiveness at filtering improper applications of inference rules, where we show substantial improvement over Pantel et al.’s system (Pantel et al., 2007). 1

Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence. We introduce the reader to the motivations for solving the ambiguity of words and provide a description of the task. We overview supervised, unsupervised, and knowledge-based approaches. The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks. Finally, applications, open problems, and future directions are discussed.

This article is aimed at quantifying the disambiguation performance of automatically acquired selectional preferences in regard to nouns, verbs, and adjectives with respect to a standard test corpus and evaluation setup (SENSEVAL-2) and to identify strengths and weaknesses. Although there is clearly a limit to coverage using preferences alone, because preferences are acquired only with respect to speci#c grammatical roles, we show that when dealing with running text, rather than isolated examples, coverage can be increased at little cost in accuracy by using the one-sense-per-discourse heuristic

This article is an introduction to some of the emerging research in the application of corpusbased learning techniques to problems in semantic interpretation. In particular, we focus on two important problems in semantic interpretation, namely, word-sense disambiguation and semantic parsing

Word Sense Disambiguation suffers from a long-standing problem of knowledge acquisition bottleneck. Although state of the art supervised systems report good accuracies for selected words, they have not been shown to be promising in terms of scalability. In this paper, we present an approach for learning coarser and more general set of concepts from a sense tagged corpus, in order to alleviate the knowledge acquisition bottleneck. We show that these general concepts can be transformed to fine grained word senses using simple heuristics, and applying the technique for recent SENSEVAL data sets shows that our approach can yield state of the art performance. 1