English

Supervised Phrase-boundary Embeddings

Computation and Language 2020-02-19 v1 Information Retrieval Machine Learning

Abstract

We propose a new word embedding model, called SPhrase, that incorporates supervised phrase information. Our method modifies traditional word embeddings by ensuring that all target words in a phrase have exactly the same context. We demonstrate that including this information within a context window produces superior embeddings for both intrinsic evaluation tasks and downstream extrinsic tasks.

Keywords

Cite

@article{arxiv.2002.06450,
  title  = {Supervised Phrase-boundary Embeddings},
  author = {Manni Singh and David Weston and Mark Levene},
  journal= {arXiv preprint arXiv:2002.06450},
  year   = {2020}
}

Comments

12 pages, 3 figures, 4 tables

R2 v1 2026-06-23T13:42:50.739Z