This paper proposes benchmarks for systems of automatic sense identification. A textual corpus in which open-class words had been tagged both syntactically and semantically was used to explore three statistical strategies for sense identification: a guessing heuristic, a most-frequent heuristic, and a co-occurrence heuristic. When no information about sense-frequencies was available, the guessi...

Sense induction seeks to automatically identify word senses of polysemous words encountered in a corpus. Unsupervised word sense induction can be viewed as a clustering problem. In this paper, we used the Hierarchical Clustering Algorithm as the classifier for word sense induction. Experiments show the system can achieve 72% F-score about train-corpus and 65% F-score about test-corpus.

The problem of the transferability of the various meanings of a polysemous word from one language to another has been studied by many researchers (e.g., Cunningham and Graham, 2000; Kellerman,1978; 1986; Viberg, 1999). The underlying theory of 'core' and 'prototype' has been used in many of psychology and psycholinguistics, such as perception (e.g. Rosch, 1973), cognitive psychology (e.g., Mill...

Finding the right representations for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This paper investigates language model representations, in which language models trained on unlabeled corpora are used to generate real-valued feature vectors for words. We investigate ngram models and probabilistic graphical models, including a nov...

Theoretical linguistic accounts of lexical ambiguity distinguish between homonymy, where words that share a lexical form have unrelated meanings, and polysemy, where the meanings are related. The present study explored the psychological reality of this theoretical assumption by asking whether there is evidence that homonyms and polysemes are represented and processed differently in the brain. W...

Natural Languages used by people for establishing proper communication consist of many words having multiple meanings known as polysemous but implies a single sense depending on the context. Word sense disambiguation is a method of determining the appropriate sense of a polysemous word in the context. WSD is almost finished for English. It is a challenging task for Indian languages since these ...

The pioneering research of G. K. Zipf on the relationship between word frequency and other word features led to the formulation of various linguistic laws. Here we focus on a couple of them: the meaning-frequency law, i.e. the tendency of more frequent words to be more polysemous, and the law of abbreviation, i.e. the tendency of more frequent words to be shorter. Here we evaluate the robustnes...

Word embeddings play a significant role in many modern NLP systems. Since learning one representation per word is problematic for polysemous words and homonymous words, researchers propose to use one embedding per word sense. Their approaches mainly train word sense embeddings on a corpus. In this paper, we propose to use word sense definitions to learn one embedding per word sense. Experimenta...

Multifunctionality of a language generates multisemanticity of words. If different senses of word are systematically related, then how these senses are derived from each other and how they should be organised to reflect their regularity in sense denotation? Before this question is addressed, in this paper an attempt is made to identify salient traits of distinctions between the polysemous and t...