#TAGSPACE: Semantic embeddings from hashtags

Jason Weston; Sumit Chopra; Keith Adams

doi:10.3115/v1/d14-1194

#TAGSPACE: Semantic embeddings from hashtags

Jason Weston, Sumit Chopra, Keith Adams

Computer Science

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

Abstract

We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags. As well as strong performance on the hashtag prediction task itself, we show that its learned representation of text (ignoring the hashtag labels) is useful for other tasks as well. To that end, we present results on a document recommendation task, where it also outperforms a number of baselines.

Original language	English (US)
Title of host publication	EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	1822-1827
Number of pages	6
ISBN (Electronic)	9781937284961
DOIs	https://doi.org/10.3115/v1/d14-1194
State	Published - 2014
Event	2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar Duration: Oct 25 2014 → Oct 29 2014

Publication series

Name	EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conference

Conference	2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
Country/Territory	Qatar
City	Doha
Period	10/25/14 → 10/29/14

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Vision and Pattern Recognition
Information Systems

Access to Document

10.3115/v1/d14-1194

Cite this

Weston, J., Chopra, S., & Adams, K. (2014). #TAGSPACE: Semantic embeddings from hashtags. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 1822-1827). (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/d14-1194

#TAGSPACE: Semantic embeddings from hashtags. / Weston, Jason; Chopra, Sumit; Adams, Keith.
EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 1822-1827 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

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

Weston, J, Chopra, S & Adams, K 2014, #TAGSPACE: Semantic embeddings from hashtags. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1822-1827, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 10/25/14. https://doi.org/10.3115/v1/d14-1194

Weston J, Chopra S, Adams K. #TAGSPACE: Semantic embeddings from hashtags. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 1822-1827. (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). doi: 10.3115/v1/d14-1194

Weston, Jason ; Chopra, Sumit ; Adams, Keith. / #TAGSPACE : Semantic embeddings from hashtags. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 1822-1827 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

@inproceedings{691c3cda86ce4cfc9b1b7327931a5554,

title = "#TAGSPACE: Semantic embeddings from hashtags",

abstract = "We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags. As well as strong performance on the hashtag prediction task itself, we show that its learned representation of text (ignoring the hashtag labels) is useful for other tasks as well. To that end, we present results on a document recommendation task, where it also outperforms a number of baselines.",

author = "Jason Weston and Sumit Chopra and Keith Adams",

note = "Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics.; 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 ; Conference date: 25-10-2014 Through 29-10-2014",

year = "2014",

doi = "10.3115/v1/d14-1194",

language = "English (US)",

series = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

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

pages = "1822--1827",

booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - #TAGSPACE

T2 - 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014

AU - Weston, Jason

AU - Chopra, Sumit

AU - Adams, Keith

PY - 2014

Y1 - 2014

N2 - We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags. As well as strong performance on the hashtag prediction task itself, we show that its learned representation of text (ignoring the hashtag labels) is useful for other tasks as well. To that end, we present results on a document recommendation task, where it also outperforms a number of baselines.

AB - We describe a convolutional neural network that learns feature representations for short textual posts using hashtags as a supervised signal. The proposed approach is trained on up to 5.5 billion words predicting 100,000 possible hashtags. As well as strong performance on the hashtag prediction task itself, we show that its learned representation of text (ignoring the hashtag labels) is useful for other tasks as well. To that end, we present results on a document recommendation task, where it also outperforms a number of baselines.

UR - http://www.scopus.com/inward/record.url?scp=84926060006&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926060006&partnerID=8YFLogxK

U2 - 10.3115/v1/d14-1194

DO - 10.3115/v1/d14-1194

M3 - Conference contribution

AN - SCOPUS:84926060006

T3 - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

SP - 1822

EP - 1827

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

Y2 - 25 October 2014 through 29 October 2014

ER -

#TAGSPACE: Semantic embeddings from hashtags

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this