Investigating different syntactic context types and context representations for learning word embeddings

Bofang Li; Tao Liu; Zhe Zhao; Buzhou Tang; Aleksandr Drozd; Anna Rogers; Xiaoyong Du

doi:10.18653/v1/d17-1257

Investigating different syntactic context types and context representations for learning word embeddings

Bofang Li
, Tao Liu
, Zhe Zhao
, Buzhou Tang
, Aleksandr Drozd
, Anna Rogers
, Xiaoyong Du

School of Information
MOE
Harbin Institute of Technology Shenzhen
Institute of Science Tokyo
University of Massachusetts Lowell

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

24 Scopus citations

Abstract

The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.

Original language	English
Title of host publication	EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
Publisher	Association for Computational Linguistics (ACL)
Pages	2421-2431
Number of pages	11
ISBN (Electronic)	9781945626838
DOIs	https://doi.org/10.18653/v1/d17-1257
State	Published - 2017
Externally published	Yes
Event	2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark Duration: 9 Sep 2017 → 11 Sep 2017

Publication series

Name	EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference	2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Country/Territory	Denmark
City	Copenhagen
Period	9/09/17 → 11/09/17

Access to Document

10.18653/v1/d17-1257

Cite this

Li, B., Liu, T., Zhao, Z., Tang, B., Drozd, A., Rogers, A., & Du, X. (2017). Investigating different syntactic context types and context representations for learning word embeddings. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 2421-2431). (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d17-1257

Li, Bofang ; Liu, Tao ; Zhao, Zhe et al. / Investigating different syntactic context types and context representations for learning word embeddings. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 2421-2431 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

@inproceedings{3b9fd3ad2be940e4aeb9aae107c30f36,

title = "Investigating different syntactic context types and context representations for learning word embeddings",

abstract = "The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.",

author = "Bofang Li and Tao Liu and Zhe Zhao and Buzhou Tang and Aleksandr Drozd and Anna Rogers and Xiaoyong Du",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 ; Conference date: 09-09-2017 Through 11-09-2017",

year = "2017",

doi = "10.18653/v1/d17-1257",

language = "英语",

series = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

publisher = "Association for Computational Linguistics (ACL)",

pages = "2421--2431",

booktitle = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

address = "澳大利亚",

}

Li, B, Liu, T, Zhao, Z, Tang, B, Drozd, A, Rogers, A & Du, X 2017, Investigating different syntactic context types and context representations for learning word embeddings. in EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), pp. 2421-2431, 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9/09/17. https://doi.org/10.18653/v1/d17-1257

Investigating different syntactic context types and context representations for learning word embeddings. / Li, Bofang; Liu, Tao; Zhao, Zhe et al.
EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 2421-2431 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Investigating different syntactic context types and context representations for learning word embeddings

AU - Li, Bofang

AU - Liu, Tao

AU - Zhao, Zhe

AU - Tang, Buzhou

AU - Drozd, Aleksandr

AU - Rogers, Anna

AU - Du, Xiaoyong

PY - 2017

Y1 - 2017

N2 - The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.

AB - The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.

UR - https://www.scopus.com/pages/publications/85068808833

U2 - 10.18653/v1/d17-1257

DO - 10.18653/v1/d17-1257

M3 - 会议稿件

AN - SCOPUS:85068808833

T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 2421

EP - 2431

BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - Association for Computational Linguistics (ACL)

T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

Y2 - 9 September 2017 through 11 September 2017

ER -

Li B, Liu T, Zhao Z, Tang B, Drozd A, Rogers A et al. Investigating different syntactic context types and context representations for learning word embeddings. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 2421-2431. (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). doi: 10.18653/v1/d17-1257

Investigating different syntactic context types and context representations for learning word embeddings

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this