A distributional semantics model for idiom detection the case of english and Russian

Jing Peng, Katsiaryna Aharodnik, Anna Feldman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

This paper describes experiments in English and Russian automatic idiom detection. Our algorithm is based on the idea that literal and idiomatic expressions appear in different contexts. This difference is captured by our distributional semantics model. We evaluate our model on both languages and compare its results. We show that our model is language-independent. We also describe a new annotated resource we created for our experiments.

Keywords

  • Corpus Annotation
  • Distributional Semantics
  • English
  • Idiom Recognition
  • Russian.

Cite this

Peng, J., Aharodnik, K., & Feldman, A. (2018). A distributional semantics model for idiom detection the case of english and Russian. In J. van den Herik, & A. P. Rocha (Eds.), ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence (pp. 675-682). (ICAART 2018 - Proceedings of the 10th International Conference on Agents and Artificial Intelligence; Vol. 2). SciTePress.