Heuristically Informed Unsupervised Idiom Usage Recognition

Changsheng Liu, Rebecca Hwa
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
Depending on the surrounding context, an idiomatic expression may be interpreted figuratively or literally. This paper proposes an unsupervised learning method for recognizing the intended usages of idioms. We treat the possible usages as a latent variable in probabilistic models and train them in a linguistically motivated feature space. Crucially, we show that distributional semantics serves as a helpful heuristic for formulating a literal usage metric to estimate the likelihood that the
more » ... is intended literally. This information can then guide the unsupervised training process for the probabilistic models. Experiments show that our overall model performs competitively against supervised methods.
doi:10.18653/v1/d18-1199 dblp:conf/emnlp/LiuH18 fatcat:7jwxjmxwb5hazn3ejpmfwqvw34