2015 RetrofittingWordVectorstoSemant

• (Faruqui et al., 2015) ⇒ Manaal Faruqui, Jesse Dodge, Sujay Kumar Jauhar, Chris Dyer, Eduard H. Hovy, and Noah A. Smith. (2015). “Retrofitting Word Vectors to Semantic Lexicons.” In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2015).

Subject Headings: SemEval-2017 Task 2; Luminoso; Retrofitting Task; Semantic Lexicon; Vector Space word Representation.

Cited By

• http://scholar.google.com/scholar?q=%222015%22+Retrofitting+Word+Vectors+to+Semantic+Lexicons

Quotes

Abstract

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This paper proposes a method for refining vector space representations using relational information from semantic lexicons by encouraging linked words to have similar vector representations, and it makes no assumptions about how the input vectors were constructed. Evaluated on a battery of standard lexical semantic evaluation tasks in several languages, we obtain substantial improvements starting with a variety of word vector models. Our refinement method outperforms prior techniques for incorporating semantic lexicons into word vector training algorithms.

BibTeX

@inproceedings{2015_RetrofittingWordVectorstoSemant,
  author    = {Manaal Faruqui and
               Jesse Dodge and
               Sujay Kumar Jauhar and
               Chris Dyer and
               Eduard H. Hovy and
               Noah A. Smith},
  editor    = {Rada Mihalcea and
               Joyce Yue Chai and
               Anoop Sarkar},
  title     = {Retrofitting Word Vectors to Semantic Lexicons},
  booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association
               for Computational Linguistics: Human Language Technologies (NAACL-HLT 2015)},
  pages     = {1606--1615},
  publisher = {The Association for Computational Linguistics},
  year      = {2015},
  url       = {https://doi.org/10.3115/v1/n15-1184},
  doi       = {10.3115/v1/n15-1184},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2015 RetrofittingWordVectorstoSemant	Eduard Hovy Chris Dyer Noah A. Smith Jesse Dodge Manaal Faruqui Sujay Kumar Jauhar			Retrofitting Word Vectors to Semantic Lexicons						2015