Sciweavers

Share
ACL
2010

Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection

9 years 11 months ago
Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection
This paper presents a probabilistic model for sense disambiguation which chooses the best sense based on the conditional probability of sense paraphrases given a context. We use a topic model to decompose this conditional probability into two conditional probabilities with latent variables. We propose three different instantiations of the model for solving sense disambiguation problems with different degrees of resource availability. The proposed models are tested on three different tasks: coarse-grained word sense disambiguation, fine-grained word sense disambiguation, and detection of literal vs. nonliteral usages of potentially idiomatic expressions. In all three cases, we outperform state-of-the-art systems either quantitatively or statistically significantly.
Linlin Li, Benjamin Roth, Caroline Sporleder
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Linlin Li, Benjamin Roth, Caroline Sporleder
Comments (0)
books