CCG: Projects

Themes | Projects | Funding | Past Projects

Lexical Semantics

[ Overview | Details | Participants | Publications ]

Overview:

There are three fundamental approaches in computing lexical similarity: (1) knowledge-rich methods, (2) vector-based models using direct distributional similarity, and (3) vector-based models using dimensionality deduction techniques. We developed several lexical similarity metrics at the word, phrasal (e.g., noun phrases, entity phrases and numerical phrases) and are also looking at a comparison between the key approaches in the context of NLP tasks such as TE.

Details:

Participants:

Relevant Publications:

X. Li, D. Roth, and Y. Tu, Phrasenet: towards context sensitive lexical semantics. Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL) (2003)