Paper: Bootstrapping Semantic Analyzers from Non-Contradictory Texts

ACL ID P10-1098
Title Bootstrapping Semantic Analyzers from Non-Contradictory Texts
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic repre- sentations. A simple and efficient infer- ence method recursively induces joint se- mantic representations for each group and discovers correspondence between lexical entries and latent semantic concepts. We consider the generative semantics-text cor- respondence model (Liang et al., 2009) and demonstrate that exploiting the non- contradiction relation between texts leads to substantial improvements over natu- ral baselines on a problem of analyzing human-written weather forecasts.