Kiela, D., Hill, F., & Clark, S. (2015). Specializing Word Embeddings for Similarity or Relatedness. Emnlp 2015, (September), 2044–2048.

We demonstrate the advantage of special- izing semanticword embeddings for either similarity or relatedness. We compare two variants of retrofitting and a joint-learning approach, and find that all three yield spe- cialized semantic spaces that capture hu- man intuitions regarding similarity and re- latedness better than unspecialized spaces. We also showthat using specialized spaces in NLP tasks and applications leads to clear improvements, for document classification and synonym selection, which rely on ei- ther similarity or relatedness but not both.

2015-01-28に文献紹介ゼミにて紹介.