Adjusting Word Embeddings with Semantic Intensity Orders

Kim, Joo-Kyung;de Marneffe, Marie-Catherine;Fosler-Lussier, Eric
(2016) Proceedings of the 1st Workshop on Representation Learning for NLP — Location: Berlin, Germany (August.2016)

Files

W16-1607.pdf
  • Open Access
  • Adobe PDF
  • 160.63 KB
Download

Details

Authors
Abstract
Semantic lexicons such as WordNet and PPDB have been used to improve the vector-based semantic representations of words by adjusting the word vectors. However, such lexicons lack semantic intensity information, inhibiting adjustment of vector spaces to better represent semantic intensity scales. In this work, we adjust word vectors using the semantic intensity information in addition to synonyms and antonyms from WordNet and PPDB, and show improved performance on judging semantic intensity orders of adjective pairs on three different human annotated datasets.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Kim, J.-K., de Marneffe, M.-C., & Fosler-Lussier, E. (2016). Adjusting Word Embeddings with Semantic Intensity Orders. Proceedings of the 1st Workshop on Representation Learning for NLP. Published. Proceedings of the 1st Workshop on Representation Learning for NLP, Berlin, Germany. https://doi.org/10.18653/v1/w16-1607 (Original work published 2016)