Measuring feature diversity in Native Language Identification

Shervin Malmasi; Aoife Cahill

Measuring feature diversity in Native Language Identification

Shervin Malmasi, Aoife Cahill

School of Computing

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

23 Citations (Scopus)

Abstract

The task of Native Language Identification (NLI) is typically solved with machine learning methods, and systems make use of a wide variety of features. Some preliminary studies have been conducted to examine the effectiveness of individual features, however, no systematic study of feature interaction has been carried out. We propose a function to measure feature independence and analyze its effectiveness on a standard NLI corpus.

Original language	English
Title of host publication	NAACL HLT 2015
Subtitle of host publication	The Tenth Workshop on Innovative Use of NLP for Building Educational Applications : proceedings of the workshop
Place of Publication	United States
Publisher	The Association for Computational Linguistics
Pages	49-55
Number of pages	7
ISBN (Print)	9781941643358
Publication status	Published - 2015
Event	Workshop on Innovative Use of NLP for Building Educational Applications (10th : 2015) - Denver, CO Duration: 4 Jun 2015 → 4 Jun 2015

Workshop

Workshop	Workshop on Innovative Use of NLP for Building Educational Applications (10th : 2015)
City	Denver, CO
Period	4/06/15 → 4/06/15

Access to Document

http://www.cs.rochester.edu/u/tetreaul/bea10proceedings.pdf

Cite this

@inproceedings{8c6d77bfb21c47628b0e87a2bfd0bccb,

title = "Measuring feature diversity in Native Language Identification",

abstract = "The task of Native Language Identification (NLI) is typically solved with machine learning methods, and systems make use of a wide variety of features. Some preliminary studies have been conducted to examine the effectiveness of individual features, however, no systematic study of feature interaction has been carried out. We propose a function to measure feature independence and analyze its effectiveness on a standard NLI corpus.",

author = "Shervin Malmasi and Aoife Cahill",

year = "2015",

language = "English",

isbn = "9781941643358",

pages = "49--55",

booktitle = "NAACL HLT 2015",

publisher = "The Association for Computational Linguistics",

note = "Workshop on Innovative Use of NLP for Building Educational Applications (10th : 2015) ; Conference date: 04-06-2015 Through 04-06-2015",

}

Malmasi, S & Cahill, A 2015, Measuring feature diversity in Native Language Identification. in NAACL HLT 2015: The Tenth Workshop on Innovative Use of NLP for Building Educational Applications : proceedings of the workshop. The Association for Computational Linguistics, United States, pp. 49-55, Workshop on Innovative Use of NLP for Building Educational Applications (10th : 2015), Denver, CO, 4/06/15. <http://www.cs.rochester.edu/u/tetreaul/bea10proceedings.pdf>

Measuring feature diversity in Native Language Identification. / Malmasi, Shervin; Cahill, Aoife.
NAACL HLT 2015: The Tenth Workshop on Innovative Use of NLP for Building Educational Applications : proceedings of the workshop. United States: The Association for Computational Linguistics, 2015. p. 49-55.

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

TY - GEN

T1 - Measuring feature diversity in Native Language Identification

AU - Malmasi, Shervin

AU - Cahill, Aoife

PY - 2015

Y1 - 2015

N2 - The task of Native Language Identification (NLI) is typically solved with machine learning methods, and systems make use of a wide variety of features. Some preliminary studies have been conducted to examine the effectiveness of individual features, however, no systematic study of feature interaction has been carried out. We propose a function to measure feature independence and analyze its effectiveness on a standard NLI corpus.

AB - The task of Native Language Identification (NLI) is typically solved with machine learning methods, and systems make use of a wide variety of features. Some preliminary studies have been conducted to examine the effectiveness of individual features, however, no systematic study of feature interaction has been carried out. We propose a function to measure feature independence and analyze its effectiveness on a standard NLI corpus.

M3 - Conference proceeding contribution

SN - 9781941643358

SP - 49

EP - 55

BT - NAACL HLT 2015

PB - The Association for Computational Linguistics

CY - United States

T2 - Workshop on Innovative Use of NLP for Building Educational Applications (10th : 2015)

Y2 - 4 June 2015 through 4 June 2015

ER -

Measuring feature diversity in Native Language Identification

Abstract

Workshop

Access to Document

Fingerprint

Cite this