CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting

Sian Gooding; Ekaterina Kochmar

CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting

Sian Gooding, Ekaterina Kochmar

Department of Computer Science

University of Cambridge

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Abstract

This paper presents the winning systems we submitted to the Complex Word Identification Shared Task 2018. We describe our best performing systems' implementations and discuss our key findings from this research. Our best-performing systems achieve an F1 score of 0.8736 on the NEWS, 0.8400 on the WIKINEWS and 0.8115 on the WIKIPEDIA test sets in the monolingual English binary classification track, and a mean absolute er- ror of 0.0558 on the NEWS, 0.0674 on the WIKINEWS and 0.0739 on the WIKIPEDIA test sets in the probabilistic track.

Original language	English
Title of host publication	Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13
Pages	184–194
Number of pages	10
Publication status	Published - 5 Jun 2018
Event	Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13 - New Orleans, USA, New Orleans, USA United States Duration: 5 Jun 2018 → 5 Jun 2018 https://www.cs.rochester.edu/~tetreaul/naacl-bea13.html

Workshop

Workshop	Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
Abbreviated title	BEA13
Country/Territory	USA United States
City	New Orleans
Period	5/06/18 → 5/06/18
Internet address	https://www.cs.rochester.edu/~tetreaul/naacl-bea13.html

Access to Document

https://www.aclweb.org/anthology/W18-0520.pdfLicence: CC BY

Cite this

CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting. / Gooding, Sian; Kochmar, Ekaterina.
Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13. 2018. p. 184–194.

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Gooding, S & Kochmar, E 2018, CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting. in Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13. pp. 184–194, Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, New Orleans, Louisiana, USA United States, 5/06/18. <https://www.aclweb.org/anthology/W18-0520.pdf>

@inproceedings{297ea20ec3b94f6bb36fbe9839081196,

title = "CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting",

abstract = "This paper presents the winning systems we submitted to the Complex Word Identification Shared Task 2018. We describe our best performing systems' implementations and discuss our key findings from this research. Our best-performing systems achieve an F1 score of 0.8736 on the NEWS, 0.8400 on the WIKINEWS and 0.8115 on the WIKIPEDIA test sets in the monolingual English binary classification track, and a mean absolute er- ror of 0.0558 on the NEWS, 0.0674 on the WIKINEWS and 0.0739 on the WIKIPEDIA test sets in the probabilistic track.",

author = "Sian Gooding and Ekaterina Kochmar",

year = "2018",

month = jun,

day = "5",

language = "English",

pages = "184–194",

booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13",

note = "Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications : BEA13, BEA13 ; Conference date: 05-06-2018 Through 05-06-2018",

url = "https://www.cs.rochester.edu/~tetreaul/naacl-bea13.html",

}

TY - GEN

T1 - CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting

AU - Gooding, Sian

AU - Kochmar, Ekaterina

PY - 2018/6/5

Y1 - 2018/6/5

N2 - This paper presents the winning systems we submitted to the Complex Word Identification Shared Task 2018. We describe our best performing systems' implementations and discuss our key findings from this research. Our best-performing systems achieve an F1 score of 0.8736 on the NEWS, 0.8400 on the WIKINEWS and 0.8115 on the WIKIPEDIA test sets in the monolingual English binary classification track, and a mean absolute er- ror of 0.0558 on the NEWS, 0.0674 on the WIKINEWS and 0.0739 on the WIKIPEDIA test sets in the probabilistic track.

AB - This paper presents the winning systems we submitted to the Complex Word Identification Shared Task 2018. We describe our best performing systems' implementations and discuss our key findings from this research. Our best-performing systems achieve an F1 score of 0.8736 on the NEWS, 0.8400 on the WIKINEWS and 0.8115 on the WIKIPEDIA test sets in the monolingual English binary classification track, and a mean absolute er- ror of 0.0558 on the NEWS, 0.0674 on the WIKINEWS and 0.0739 on the WIKIPEDIA test sets in the probabilistic track.

M3 - Chapter in a published conference proceeding

SP - 184

EP - 194

BT - Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications: BEA13

T2 - Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications

Y2 - 5 June 2018 through 5 June 2018

ER -

CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting

Abstract

Workshop

Access to Document

Fingerprint

Cite this