In this paper we define two parallel data sets based on pseudowords, extracted from the same corpus. They both consist of word-centered graphs for each of 1225 different pseudowords, and use respectively first-order co-occurrences and secondorder semantic similarities. We propose an evaluation framework on these data sets for graph-based Word Sense Induction (WSI) focused on the case of coarseg...

In Information Retrieval (IR), the semantic gap is the difference between what computers store and what users expect via their queries. There are several reasons for the existence of those gaps such as homonymy and synonymy in text retrieval, or the typical difference between low-level representations and keyword-based queries in image retrieval. The objective of this work is to close these gap...

Unsupervised word representations are very useful in NLP tasks both as inputs to learning algorithms and as extra word features in NLP systems. However, most of these models are built with only local context and one representation per word. This is problematic because words are often polysemous and global context can also provide useful information for learning word meanings. We present a new n...

Nowadays, new technologies contribute to make Information Systems (IS) more and more complex. So, IS modelling requires the use of a referential to resolve some problems and conflicts due to the ignorance of the field to be modelled, to the complexity and the multitude of the concepts used. These concepts come from heterogeneous sources. This heterogeneity often involves semantic ambiguities (f...

Most sentence embedding models typically represent each sentence only using word surface, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance representation capability of sentence, we employ conceptualization model to assign associated concepts for each sentence in the text corpus, and then learn conceptual sentence embedding (CSE). Hence, this se...

While polysemy is a form of ambiguity that can complicate natural language processing, it is also a rich lexical resource that yields useful insights into the mapping between words and concepts. WordNet, a comprehensive lexical knowledge-base of English word meanings, is replete with instances of polysemy, but also contains many instances of homonymy, and fails to distinguish between both kinds...

In this paper we report on experiments using WordNet synset tags to evaluate the semantic properties of the verb classes cataloged by Levin (1993). This paper represents ongoing research begun at the University of Pennsylvania (Rosenzweig and Dang, 1997; Palmer, Rosenzweig, and Dang, 1997) and the University of Maryland (Dorr and Jones, 1996b; Dorr and Jones, 1996a; Dorr and Jones, 1996c). Usin...