Modelling function words improves unsupervised word segmentation

Mark Johnson, Anne Christophe, Katherine Demuth, Emmanuel Dupoux

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Inspired by experimental psychological findings suggesting that function words play a special role in word learning, we make a simple modification to an Adaptor Grammar based Bayesian word segmentation model to allow it to learn sequences of monosyllabic "function words" at the beginnings and endings of collocations of (possibly multi-syllabic) words. This modification improves unsupervised word segmentation on the standard Bernstein- Ratner (1987) corpus of child-directed English by more than 4% token f-score compared to a model identical except that it does not special-case "function words", setting a new state-of-the-art of 92.4% token f-score. Our function word model assumes that function words appear at the left periphery, and while this is true of languages such as English, it is not true universally. We show that a learner can use Bayesian model selection to determine the location of function words in their language, even though the input to the model only consists of unsegmented sequences of phones. Thus our computational models support the hypothesis that function words play a special role in word learning.

LanguageEnglish
Title of host publicationLong Papers
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics (ACL)
Pages282-292
Number of pages11
Volume1
ISBN (Print)9781937284725
Publication statusPublished - 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: 22 Jun 201427 Jun 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period22/06/1427/06/14

Fingerprint

language
Modeling
Function Words
Word Segmentation
segmentation
learning
grammar
Wordplay
Word Learning
Language
Phone
Left Periphery
Bayesian Model
Collocation
Model Selection
Computational Model
Grammar
Psychological

Cite this

Johnson, M., Christophe, A., Demuth, K., & Dupoux, E. (2014). Modelling function words improves unsupervised word segmentation. In Long Papers (Vol. 1, pp. 282-292). Stroudsburg, PA: Association for Computational Linguistics (ACL).
Johnson, Mark ; Christophe, Anne ; Demuth, Katherine ; Dupoux, Emmanuel. / Modelling function words improves unsupervised word segmentation. Long Papers. Vol. 1 Stroudsburg, PA : Association for Computational Linguistics (ACL), 2014. pp. 282-292
@inproceedings{0cfea2a357c84d4ba6548e387025ba2e,
title = "Modelling function words improves unsupervised word segmentation",
abstract = "Inspired by experimental psychological findings suggesting that function words play a special role in word learning, we make a simple modification to an Adaptor Grammar based Bayesian word segmentation model to allow it to learn sequences of monosyllabic {"}function words{"} at the beginnings and endings of collocations of (possibly multi-syllabic) words. This modification improves unsupervised word segmentation on the standard Bernstein- Ratner (1987) corpus of child-directed English by more than 4{\%} token f-score compared to a model identical except that it does not special-case {"}function words{"}, setting a new state-of-the-art of 92.4{\%} token f-score. Our function word model assumes that function words appear at the left periphery, and while this is true of languages such as English, it is not true universally. We show that a learner can use Bayesian model selection to determine the location of function words in their language, even though the input to the model only consists of unsegmented sequences of phones. Thus our computational models support the hypothesis that function words play a special role in word learning.",
author = "Mark Johnson and Anne Christophe and Katherine Demuth and Emmanuel Dupoux",
year = "2014",
language = "English",
isbn = "9781937284725",
volume = "1",
pages = "282--292",
booktitle = "Long Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

Johnson, M, Christophe, A, Demuth, K & Dupoux, E 2014, Modelling function words improves unsupervised word segmentation. in Long Papers. vol. 1, Association for Computational Linguistics (ACL), Stroudsburg, PA, pp. 282-292, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, United States, 22/06/14.

Modelling function words improves unsupervised word segmentation. / Johnson, Mark; Christophe, Anne; Demuth, Katherine; Dupoux, Emmanuel.

Long Papers. Vol. 1 Stroudsburg, PA : Association for Computational Linguistics (ACL), 2014. p. 282-292.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Modelling function words improves unsupervised word segmentation

AU - Johnson, Mark

AU - Christophe, Anne

AU - Demuth, Katherine

AU - Dupoux, Emmanuel

PY - 2014

Y1 - 2014

N2 - Inspired by experimental psychological findings suggesting that function words play a special role in word learning, we make a simple modification to an Adaptor Grammar based Bayesian word segmentation model to allow it to learn sequences of monosyllabic "function words" at the beginnings and endings of collocations of (possibly multi-syllabic) words. This modification improves unsupervised word segmentation on the standard Bernstein- Ratner (1987) corpus of child-directed English by more than 4% token f-score compared to a model identical except that it does not special-case "function words", setting a new state-of-the-art of 92.4% token f-score. Our function word model assumes that function words appear at the left periphery, and while this is true of languages such as English, it is not true universally. We show that a learner can use Bayesian model selection to determine the location of function words in their language, even though the input to the model only consists of unsegmented sequences of phones. Thus our computational models support the hypothesis that function words play a special role in word learning.

AB - Inspired by experimental psychological findings suggesting that function words play a special role in word learning, we make a simple modification to an Adaptor Grammar based Bayesian word segmentation model to allow it to learn sequences of monosyllabic "function words" at the beginnings and endings of collocations of (possibly multi-syllabic) words. This modification improves unsupervised word segmentation on the standard Bernstein- Ratner (1987) corpus of child-directed English by more than 4% token f-score compared to a model identical except that it does not special-case "function words", setting a new state-of-the-art of 92.4% token f-score. Our function word model assumes that function words appear at the left periphery, and while this is true of languages such as English, it is not true universally. We show that a learner can use Bayesian model selection to determine the location of function words in their language, even though the input to the model only consists of unsegmented sequences of phones. Thus our computational models support the hypothesis that function words play a special role in word learning.

UR - http://www.scopus.com/inward/record.url?scp=84906925748&partnerID=8YFLogxK

M3 - Conference proceeding contribution

SN - 9781937284725

VL - 1

SP - 282

EP - 292

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA

ER -

Johnson M, Christophe A, Demuth K, Dupoux E. Modelling function words improves unsupervised word segmentation. In Long Papers. Vol. 1. Stroudsburg, PA: Association for Computational Linguistics (ACL). 2014. p. 282-292