@inproceedings{liu-etal-2017-learning,
title = "Learning Character-level Compositionality with Visual Features",
author = "Liu, Frederick and
Lu, Han and
Lo, Chieh and
Neubig, Graham",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1188",
doi = "10.18653/v1/P17-1188",
pages = "2059--2068",
abstract = "Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry topical content which resulting in embeddings that are coherent in visual space.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2017-learning">
<titleInfo>
<title>Learning Character-level Compositionality with Visual Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frederick</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chieh</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry topical content which resulting in embeddings that are coherent in visual space.</abstract>
<identifier type="citekey">liu-etal-2017-learning</identifier>
<identifier type="doi">10.18653/v1/P17-1188</identifier>
<location>
<url>https://aclanthology.org/P17-1188</url>
</location>
<part>
<date>2017-jul</date>
<extent unit="page">
<start>2059</start>
<end>2068</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Character-level Compositionality with Visual Features
%A Liu, Frederick
%A Lu, Han
%A Lo, Chieh
%A Neubig, Graham
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 jul
%I Association for Computational Linguistics
%C Vancouver, Canada
%F liu-etal-2017-learning
%X Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry topical content which resulting in embeddings that are coherent in visual space.
%R 10.18653/v1/P17-1188
%U https://aclanthology.org/P17-1188
%U https://doi.org/10.18653/v1/P17-1188
%P 2059-2068
Markdown (Informal)
[Learning Character-level Compositionality with Visual Features](https://aclanthology.org/P17-1188) (Liu et al., ACL 2017)
ACL
- Frederick Liu, Han Lu, Chieh Lo, and Graham Neubig. 2017. Learning Character-level Compositionality with Visual Features. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2059–2068, Vancouver, Canada. Association for Computational Linguistics.