Building a Lexical Knowledge-Base of Near-Synonym Differences Diana Inkpen Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2004 Current natural language generation or machine translation systems cannot distinguish among near-synonyms—words that share the same core meaning but vary in their lexical nuances. This is due to a lack of knowledge about differences b...

In this paper, we address the issue of integrating semantic lexicons into NLG systems and argue that the problem of lexical choice in generation can be approached only by such an integration. We take the approach of Generative Lexicon Theory (GLT) (Pnstejovsky, 1991, 1994c) which provides a system involving four levels of representation connected by a set of generative devices accounting for a ...

Identifying collocations in a text (e.g., break record) and correctly translating them (battre record vs. *casser record) represent key issues in machine translation, notably because of their prevalence in language and their syntactic flexibility. This article describes a method for discovering translation equivalents for collocations from parallel corpora, aimed at increasing the lexical cover...

Resumen. Lexical functions formalize semantic and syntactic relations between lexical units, given that meaning of an individual word largely depends on various relations connecting it to other words in context. Collocational relation is a type of institutionalized lexical relations that holds between the base and its partner in a collocation in contrast to free word combination where both word...

A challenging task in Chinese collocation extraction is to improve both the precision and recall rate. Most lexical statistical methods including Xtract face the problem of unable to extract collocations with lower frequencies than a given threshold. This paper presents a method where HowNet is used to find synonyms using a similarity function. Based on such synonym information, we have success...

Collocation extraction systems based on pure statistical methods suffer from two major problems. The first problem is their relatively low precision and recall rates. The second problem is their difficulty in dealing with sparse collocations. In order to improve performance, both statistical and lexicographic approaches should be considered. This paper presents a new method to extract synonymou...

Collocations pose specific problems in translation (both human and machine translation). For the native speaker of English it may be obvious that you ’pay attention’, but for a native speaker of Dutch it would have been much simpler if in English people ’donated attention.’ Within an MT system, we can deal with these mismatches in different ways. Simply adding the entry to our bilingual diction...

In a collocation, the choice of one lexical item depends on the choice made for another. This poses a problem for simple approaches to lexicalisation in natural language generation systems. In the Meaning-Text framework, recurrent patterns of collocations have been characterised by lexical functions, which offer an elegant way of describing these relationships. Previous work has shown that usin...

We 1 describe our attempts to automatically extract raw material for a dictionary of German noun-verb collocations from large corpora of newspaper text. Such a dictionary should be about collocations and it should include a description of their linguistic properties, rather than listing the mere lexical cooccurrence. Since most statistical collocation nding tools do not provide other than lexic...

The paper addressed the question how the paraphrasing of synonyms can be linked with a fine-gained ontology based data representation. Our challenge is to identify for a set of synonyms (including terms and multiword expressions) the best lexical paraphrases suitable for given contexts. Our hypothesis is that: i. the minimal context in which the paraphrasing can be validated is different for di...