@inproceedings{sommerauer-2020-penguin,
title = "Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models",
author = "Sommerauer, Pia",
editor = "Rijhwani, Shruti and
Liu, Jiangming and
Wang, Yizhong and
Dror, Rotem",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-srw.18/",
doi = "10.18653/v1/2020.acl-srw.18",
pages = "134--142",
abstract = "What do powerful models of word mean- ing created from distributional data (e.g. Word2vec (Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent? What causes words to be similar in the semantic space? What type of information is lacking? This thesis proposal presents a framework for investigating the information encoded in distributional semantic models. Several analysis methods have been suggested, but they have been shown to be limited and are not well understood. This approach pairs observations made on actual corpora with insights obtained from data manipulation experiments. The expected outcome is a better understanding of (1) the semantic information we can infer purely based on linguistic co-occurrence patterns and (2) the potential of distributional semantic models to pick up linguistic evidence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sommerauer-2020-penguin">
<titleInfo>
<title>Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pia</namePart>
<namePart type="family">Sommerauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</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>What do powerful models of word mean- ing created from distributional data (e.g. Word2vec (Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent? What causes words to be similar in the semantic space? What type of information is lacking? This thesis proposal presents a framework for investigating the information encoded in distributional semantic models. Several analysis methods have been suggested, but they have been shown to be limited and are not well understood. This approach pairs observations made on actual corpora with insights obtained from data manipulation experiments. The expected outcome is a better understanding of (1) the semantic information we can infer purely based on linguistic co-occurrence patterns and (2) the potential of distributional semantic models to pick up linguistic evidence.</abstract>
<identifier type="citekey">sommerauer-2020-penguin</identifier>
<identifier type="doi">10.18653/v1/2020.acl-srw.18</identifier>
<location>
<url>https://aclanthology.org/2020.acl-srw.18/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>134</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models
%A Sommerauer, Pia
%Y Rijhwani, Shruti
%Y Liu, Jiangming
%Y Wang, Yizhong
%Y Dror, Rotem
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F sommerauer-2020-penguin
%X What do powerful models of word mean- ing created from distributional data (e.g. Word2vec (Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent? What causes words to be similar in the semantic space? What type of information is lacking? This thesis proposal presents a framework for investigating the information encoded in distributional semantic models. Several analysis methods have been suggested, but they have been shown to be limited and are not well understood. This approach pairs observations made on actual corpora with insights obtained from data manipulation experiments. The expected outcome is a better understanding of (1) the semantic information we can infer purely based on linguistic co-occurrence patterns and (2) the potential of distributional semantic models to pick up linguistic evidence.
%R 10.18653/v1/2020.acl-srw.18
%U https://aclanthology.org/2020.acl-srw.18/
%U https://doi.org/10.18653/v1/2020.acl-srw.18
%P 134-142
Markdown (Informal)
[Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models](https://aclanthology.org/2020.acl-srw.18/) (Sommerauer, ACL 2020)
ACL