@inproceedings{wijnholds-etal-2020-representation,
title = "Representation Learning for Type-Driven Composition",
author = "Wijnholds, Gijs and
Sadrzadeh, Mehrnoosh and
Clark, Stephen",
booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.conll-1.24",
doi = "10.18653/v1/2020.conll-1.24",
pages = "313--324",
abstract = "This paper is about learning word representations using grammatical type information. We use the syntactic types of Combinatory Categorial Grammar to develop multilinear representations, i.e. maps with n arguments, for words with different functional types. The multilinear maps of words compose with each other to form sentence representations. We extend the skipgram algorithm from vectors to multi- linear maps to learn these representations and instantiate it on unary and binary maps for transitive verbs. These are evaluated on verb and sentence similarity and disambiguation tasks and a subset of the SICK relatedness dataset. Our model performs better than previous type- driven models and is competitive with state of the art representation learning methods such as BERT and neural sentence encoders.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wijnholds-etal-2020-representation">
<titleInfo>
<title>Representation Learning for Type-Driven Composition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gijs</namePart>
<namePart type="family">Wijnholds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoosh</namePart>
<namePart type="family">Sadrzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Conference on Computational Natural Language Learning</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper is about learning word representations using grammatical type information. We use the syntactic types of Combinatory Categorial Grammar to develop multilinear representations, i.e. maps with n arguments, for words with different functional types. The multilinear maps of words compose with each other to form sentence representations. We extend the skipgram algorithm from vectors to multi- linear maps to learn these representations and instantiate it on unary and binary maps for transitive verbs. These are evaluated on verb and sentence similarity and disambiguation tasks and a subset of the SICK relatedness dataset. Our model performs better than previous type- driven models and is competitive with state of the art representation learning methods such as BERT and neural sentence encoders.</abstract>
<identifier type="citekey">wijnholds-etal-2020-representation</identifier>
<identifier type="doi">10.18653/v1/2020.conll-1.24</identifier>
<location>
<url>https://aclanthology.org/2020.conll-1.24</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>313</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representation Learning for Type-Driven Composition
%A Wijnholds, Gijs
%A Sadrzadeh, Mehrnoosh
%A Clark, Stephen
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F wijnholds-etal-2020-representation
%X This paper is about learning word representations using grammatical type information. We use the syntactic types of Combinatory Categorial Grammar to develop multilinear representations, i.e. maps with n arguments, for words with different functional types. The multilinear maps of words compose with each other to form sentence representations. We extend the skipgram algorithm from vectors to multi- linear maps to learn these representations and instantiate it on unary and binary maps for transitive verbs. These are evaluated on verb and sentence similarity and disambiguation tasks and a subset of the SICK relatedness dataset. Our model performs better than previous type- driven models and is competitive with state of the art representation learning methods such as BERT and neural sentence encoders.
%R 10.18653/v1/2020.conll-1.24
%U https://aclanthology.org/2020.conll-1.24
%U https://doi.org/10.18653/v1/2020.conll-1.24
%P 313-324
Markdown (Informal)
[Representation Learning for Type-Driven Composition](https://aclanthology.org/2020.conll-1.24) (Wijnholds et al., CoNLL 2020)
ACL
- Gijs Wijnholds, Mehrnoosh Sadrzadeh, and Stephen Clark. 2020. Representation Learning for Type-Driven Composition. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 313–324, Online. Association for Computational Linguistics.