In this paper, we present a method for assigning examplesentences to each sense of words in WordNet. The key idea is thatthe method assigns each sense of a word w collected from not onlythe sentences containing w, but also sentences containing words withsemantically related to w. Because a collection of a context of thetarget word w is a similar syntactic behavior, even coll...

Words mean different things in different contexts, a phenomenon called polysemy. People talk about lines of both people and poetry, and about both long distances and long times. Polysemy lets a limited vocabulary capture a great variety of experiences, while highlighting commonalities. But how is this achieved? Are polysemous senses contextually driven modifications of core meanings, or must ea...

Word sense disambiguation is one of the most important open problems in natural language processing applications such as information retrieval and machine translation. Many approach strategies can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledgebased, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy...

It is widely acknowledged that texts are not translated word by word, but unit by unit. Single words are polysemous and therefore ambiguous in translation. Corpus linguistics, in monolingual context, has replaced the traditional basic notion of meaning (words) with the extended unit of meaning. Accordingly, this paper argues that in bilingual context, the translation unit, as the counterpart co...

A character corresponds roughly to a morpheme in Chinese, and it usually takes on multiple meanings. In this paper, we aimed at capturing the multiple meanings of a Chinese morpheme across polymorphemic words in a growing semantic micro-space. Using Latent Semantic Analysis (LSA), we created several nested LSA semantic micro-spaces of increasing size. The term-document matrix of the smallest se...

This paper proposes a new semantic representation and its associated similarity measure. The representation expresses textual context observed in a context of a certain term as a network where nodes are terms and edges are the number of cooccurrences between connected terms. To compare terms represented in networks, a graph kernel is adopted as a similarity measure. The proposed representation ...

There have been some works that learn a lexicon together with the corpus to improve the word embeddings. However, they either model the lexicon separately but update the neural networks for both the corpus and the lexicon by the same likelihood, or minimize the distance between all of the synonym pairs in the lexicon. Such methods do not consider the relatedness and difference of the corpus and...

Word Sense Disambiguation (WSD) is an intermediate task that serves as a means to an end defined by the application in which it is to be used. However, different applications have varying disambiguation needs which should have an impact on the choice of the method and of the sense inventory used. The tendency towards application-oriented WSD becomes more and more evident, mostly because of the ...

Normal language user’s word-association intuition (e.g. drunken – stagger) raises questions about the mental lexicon organization and its application for natural language processing tasks. We present an automatic contextually related words (contexonym) organizing model (ACOM) that reflects this intuition, giving one of the possible answers to this question. Trained on large corpora, the model (...

Bilingual dictionaries provide basic translation equivalents for a headword and typically limit the set of equivalents to words of the same part of speech as the headword. However, words taken in their contexts can be translated in many more ways. At the same time, equivalents listed in dictionaries are not adequate in many contexts, because of the contextual and collocational sensitivity of ta...