DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity

Md Arafat Sultan; Steven Bethard; Tamara Sumner

doi:10.18653/v1/s16-1099

DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity

Md Arafat Sultan, Steven Bethard, Tamara Sumner

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

4 Scopus citations

Abstract

We describe a set of systems submitted to the SemEval-2016 English Semantic Textual Similarity (STS) task. Given two English sentences, the task is to compute the degree of their semantic similarity. Each of our systems uses the SemEval 2012-2015 STS datasets to train a ridge regression model that combines different measures of similarity. Our best system demonstrates 73.6% correlation with average human annotations across five test sets.

Original language	English (US)
Title of host publication	SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings
Publisher	Association for Computational Linguistics (ACL)
Pages	650-655
Number of pages	6
ISBN (Electronic)	9781941643952
DOIs	https://doi.org/10.18653/v1/s16-1099
State	Published - 2016
Externally published	Yes
Event	10th International Workshop on Semantic Evaluation, SemEval 2016 - San Diego, United States Duration: Jun 16 2016 → Jun 17 2016

Publication series

Name	SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

Conference

Conference	10th International Workshop on Semantic Evaluation, SemEval 2016
Country/Territory	United States
City	San Diego
Period	6/16/16 → 6/17/16

ASJC Scopus subject areas

Theoretical Computer Science
Computational Theory and Mathematics
Computer Science Applications

Access to Document

10.18653/v1/s16-1099

Cite this

Sultan, M. A., Bethard, S., & Sumner, T. (2016). DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity. In SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings (pp. 650-655). (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s16-1099

DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity. / Sultan, Md Arafat; Bethard, Steven; Sumner, Tamara.
SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. Association for Computational Linguistics (ACL), 2016. p. 650-655 (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings).

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

Sultan, MA, Bethard, S & Sumner, T 2016, DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity. in SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings, Association for Computational Linguistics (ACL), pp. 650-655, 10th International Workshop on Semantic Evaluation, SemEval 2016, San Diego, United States, 6/16/16. https://doi.org/10.18653/v1/s16-1099

@inproceedings{3a06dbecaf854f08833968c2a19b83b2,

title = "DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity",

abstract = "We describe a set of systems submitted to the SemEval-2016 English Semantic Textual Similarity (STS) task. Given two English sentences, the task is to compute the degree of their semantic similarity. Each of our systems uses the SemEval 2012-2015 STS datasets to train a ridge regression model that combines different measures of similarity. Our best system demonstrates 73.6% correlation with average human annotations across five test sets.",

author = "Sultan, {Md Arafat} and Steven Bethard and Tamara Sumner",

note = "Publisher Copyright: {\textcopyright} 2016 Association for Computational Linguistics.; 10th International Workshop on Semantic Evaluation, SemEval 2016 ; Conference date: 16-06-2016 Through 17-06-2016",

year = "2016",

doi = "10.18653/v1/s16-1099",

language = "English (US)",

series = "SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings",

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

pages = "650--655",

booktitle = "SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings",

}

TY - GEN

T1 - DLS@CU at SemEval-2016 task 1

T2 - 10th International Workshop on Semantic Evaluation, SemEval 2016

AU - Sultan, Md Arafat

AU - Bethard, Steven

AU - Sumner, Tamara

PY - 2016

Y1 - 2016

N2 - We describe a set of systems submitted to the SemEval-2016 English Semantic Textual Similarity (STS) task. Given two English sentences, the task is to compute the degree of their semantic similarity. Each of our systems uses the SemEval 2012-2015 STS datasets to train a ridge regression model that combines different measures of similarity. Our best system demonstrates 73.6% correlation with average human annotations across five test sets.

AB - We describe a set of systems submitted to the SemEval-2016 English Semantic Textual Similarity (STS) task. Given two English sentences, the task is to compute the degree of their semantic similarity. Each of our systems uses the SemEval 2012-2015 STS datasets to train a ridge regression model that combines different measures of similarity. Our best system demonstrates 73.6% correlation with average human annotations across five test sets.

UR - http://www.scopus.com/inward/record.url?scp=85035775083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035775083&partnerID=8YFLogxK

U2 - 10.18653/v1/s16-1099

DO - 10.18653/v1/s16-1099

M3 - Conference contribution

AN - SCOPUS:85035775083

T3 - SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

SP - 650

EP - 655

BT - SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

PB - Association for Computational Linguistics (ACL)

Y2 - 16 June 2016 through 17 June 2016

ER -

DLS@CU at SemEval-2016 task 1: Supervised models of sentence similarity

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this