Modeling language evolution with codes that utilize context and phonetic features

Javad Nouri; Roman Yangarber

Modeling language evolution with codes that utilize context and phonetic features

Department of Computer Science

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

Abstract

We present methods for investigating processes of evolution in a language family by modeling relationships among the observed languages.

The models aim to find regularities---regular correspondences in lexical data. We present an algorithm which codes the data using phonetic features of sounds, and learns long-range contextual rules that condition recurrent sound correspondences between languages. This gives us a measure of model quality: better models find more regularity in the data. We also present a procedure for imputing unseen data, which provides another method of model comparison. Our experiments demonstrate improvements in performance compared to prior work.

Original language	English
Title of host publication	The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL) : Proceedings of the Conference
Number of pages	10
Place of Publication	Stroudsburg, PA
Publisher	The Association for Computational Linguistics
Publication date	2016
Pages	136-145
ISBN (Print)	978-1-945626-19-7
Publication status	Published - 2016
MoE publication type	A4 Article in conference proceedings
Event	Conference on Computational Natural Language Learning - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 Conference number: 20

Bibliographical note

CoNLL 2016

Fields of Science

113 Computer and information sciences

Access to Document

http://aclweb.org/anthology/K/K16/K16-1014.pdf

Cite this

@inproceedings{757ae4cf98644a65816c6cf0ffbcd526,

title = "Modeling language evolution with codes that utilize context and phonetic features",

abstract = "We present methods for investigating processes of evolution in a language family by modeling relationships among the observed languages.The models aim to find regularities---regular correspondences in lexical data. We present an algorithm which codes the data using phonetic features of sounds, and learns long-range contextual rules that condition recurrent sound correspondences between languages. This gives us a measure of model quality: better models find more regularity in the data. We also present a procedure for imputing unseen data, which provides another method of model comparison. Our experiments demonstrate improvements in performance compared to prior work.",

keywords = "113 Computer and information sciences",

author = "Javad Nouri and Roman Yangarber",

note = "CoNLL 2016 ; Conference on Computational Natural Language Learning ; Conference date: 11-08-2016 Through 12-08-2016",

year = "2016",

language = "English",

isbn = "978-1-945626-19-7",

pages = "136--145",

booktitle = "The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL)",

publisher = "The Association for Computational Linguistics",

address = "United States",

}

Nouri, J & Yangarber, R 2016, Modeling language evolution with codes that utilize context and phonetic features. in The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL): Proceedings of the Conference. The Association for Computational Linguistics, Stroudsburg, PA, pp. 136-145, Conference on Computational Natural Language Learning, Berlin, Germany, 11/08/2016. <http://aclweb.org/anthology/K/K16/K16-1014.pdf>

Modeling language evolution with codes that utilize context and phonetic features. / Nouri, Javad; Yangarber, Roman.

The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL): Proceedings of the Conference. Stroudsburg, PA : The Association for Computational Linguistics, 2016. p. 136-145.

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

TY - GEN

T1 - Modeling language evolution with codes that utilize context and phonetic features

AU - Nouri, Javad

AU - Yangarber, Roman

N1 - Conference code: 20

PY - 2016

Y1 - 2016

N2 - We present methods for investigating processes of evolution in a language family by modeling relationships among the observed languages.The models aim to find regularities---regular correspondences in lexical data. We present an algorithm which codes the data using phonetic features of sounds, and learns long-range contextual rules that condition recurrent sound correspondences between languages. This gives us a measure of model quality: better models find more regularity in the data. We also present a procedure for imputing unseen data, which provides another method of model comparison. Our experiments demonstrate improvements in performance compared to prior work.

AB - We present methods for investigating processes of evolution in a language family by modeling relationships among the observed languages.The models aim to find regularities---regular correspondences in lexical data. We present an algorithm which codes the data using phonetic features of sounds, and learns long-range contextual rules that condition recurrent sound correspondences between languages. This gives us a measure of model quality: better models find more regularity in the data. We also present a procedure for imputing unseen data, which provides another method of model comparison. Our experiments demonstrate improvements in performance compared to prior work.

KW - 113 Computer and information sciences

UR - http://www.clips.uantwerpen.be/drupal7/sites/conll.org/files/program2016/185.html

UR - http://aclweb.org/anthology/K/K16/K16-1.pdf

M3 - Conference contribution

SN - 978-1-945626-19-7

SP - 136

EP - 145

BT - The 20th SIGNLL Conference on Computational Natural Language Learning (CoNLL)

PB - The Association for Computational Linguistics

CY - Stroudsburg, PA

T2 - Conference on Computational Natural Language Learning

Y2 - 11 August 2016 through 12 August 2016

ER -

Modeling language evolution with codes that utilize context and phonetic features

Abstract

Bibliographical note

Fields of Science

Access to Document

Other files and links

LLL: Language Learning Lab

Revita: Language learning and AI

Cite this

Modeling language evolution with codes that utilize context and phonetic features

Abstract

Bibliographical note

Fields of Science

Access to Document

Other files and links

Projects

LLL: Language Learning Lab

Revita: Language learning and AI

Cite this