Paper: Improving Lexical Semantics for Sentential Semantics: Modeling Selectional Preference and Similar Words in a Latent Variable Model

ACL ID N13-1089
Title Improving Lexical Semantics for Sentential Semantics: Modeling Selectional Preference and Similar Words in a Latent Variable Model
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2013
Authors

Sentence Similarity [SS] computes a similar- ity score between two sentences. The SS task differs from document level semantics tasks in that it features the sparsity of words in a data unit, i.e. a sentence. Accordingly it is crucial to robustly model each word in a sen- tence to capture the complete semantic picture of the sentence. In this paper, we hypoth- esize that by better modeling lexical seman- tics we can obtain better sentential semantics. We incorporate both corpus-based (selectional preference information) and knowledge-based (similar words extracted in a dictionary) lex- ical semantics into a latent variable model. The experiments show state-of-the-art perfor- mance among unsupervised systems on two SS datasets.