@inproceedings{alhama-etal-2020-evaluating,
title = "Evaluating Word Embeddings for Language Acquisition",
author = "Alhama, Raquel G. and
Rowland, Caroline and
Kidd, Evan",
editor = "Chersoni, Emmanuele and
Jacobs, Cassandra and
Oseki, Yohei and
Pr{\'e}vot, Laurent and
Santus, Enrico",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.cmcl-1.4",
doi = "10.18653/v1/2020.cmcl-1.4",
pages = "38--42",
abstract = "Continuous vector word representations (or word embeddings) have shown success in capturing semantic relations between words, as evidenced with evaluation against behavioral data of adult performance on semantic tasks (Pereira et al. 2016). Adult semantic knowledge is the endpoint of a language acquisition process; thus, a relevant question is whether these models can also capture emerging word representations of young language learners. However, the data of semantic knowledge of children is scarce or non-existent for some age groups. In this paper, we propose to bridge this gap by using Age of Acquisition norms to evaluate word embeddings learnt from child-directed input. We present two methods that evaluate word embeddings in terms of (a) the semantic neighbourhood density of learnt words, and (b) the convergence to adult word associations. We apply our methods to bag-of-words models, and we find that (1) children acquire words with fewer semantic neighbours earlier, and (2) young learners only attend to very local context. These findings provide converging evidence for validity of our methods in understanding the prerequisite features for a distributional model of word learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alhama-etal-2020-evaluating">
<titleInfo>
<title>Evaluating Word Embeddings for Language Acquisition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Alhama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Rowland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evan</namePart>
<namePart type="family">Kidd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cassandra</namePart>
<namePart type="family">Jacobs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Prévot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Continuous vector word representations (or word embeddings) have shown success in capturing semantic relations between words, as evidenced with evaluation against behavioral data of adult performance on semantic tasks (Pereira et al. 2016). Adult semantic knowledge is the endpoint of a language acquisition process; thus, a relevant question is whether these models can also capture emerging word representations of young language learners. However, the data of semantic knowledge of children is scarce or non-existent for some age groups. In this paper, we propose to bridge this gap by using Age of Acquisition norms to evaluate word embeddings learnt from child-directed input. We present two methods that evaluate word embeddings in terms of (a) the semantic neighbourhood density of learnt words, and (b) the convergence to adult word associations. We apply our methods to bag-of-words models, and we find that (1) children acquire words with fewer semantic neighbours earlier, and (2) young learners only attend to very local context. These findings provide converging evidence for validity of our methods in understanding the prerequisite features for a distributional model of word learning.</abstract>
<identifier type="citekey">alhama-etal-2020-evaluating</identifier>
<identifier type="doi">10.18653/v1/2020.cmcl-1.4</identifier>
<location>
<url>https://aclanthology.org/2020.cmcl-1.4</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>38</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Word Embeddings for Language Acquisition
%A Alhama, Raquel G.
%A Rowland, Caroline
%A Kidd, Evan
%Y Chersoni, Emmanuele
%Y Jacobs, Cassandra
%Y Oseki, Yohei
%Y Prévot, Laurent
%Y Santus, Enrico
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F alhama-etal-2020-evaluating
%X Continuous vector word representations (or word embeddings) have shown success in capturing semantic relations between words, as evidenced with evaluation against behavioral data of adult performance on semantic tasks (Pereira et al. 2016). Adult semantic knowledge is the endpoint of a language acquisition process; thus, a relevant question is whether these models can also capture emerging word representations of young language learners. However, the data of semantic knowledge of children is scarce or non-existent for some age groups. In this paper, we propose to bridge this gap by using Age of Acquisition norms to evaluate word embeddings learnt from child-directed input. We present two methods that evaluate word embeddings in terms of (a) the semantic neighbourhood density of learnt words, and (b) the convergence to adult word associations. We apply our methods to bag-of-words models, and we find that (1) children acquire words with fewer semantic neighbours earlier, and (2) young learners only attend to very local context. These findings provide converging evidence for validity of our methods in understanding the prerequisite features for a distributional model of word learning.
%R 10.18653/v1/2020.cmcl-1.4
%U https://aclanthology.org/2020.cmcl-1.4
%U https://doi.org/10.18653/v1/2020.cmcl-1.4
%P 38-42
Markdown (Informal)
[Evaluating Word Embeddings for Language Acquisition](https://aclanthology.org/2020.cmcl-1.4) (Alhama et al., CMCL 2020)
ACL
- Raquel G. Alhama, Caroline Rowland, and Evan Kidd. 2020. Evaluating Word Embeddings for Language Acquisition. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 38–42, Online. Association for Computational Linguistics.