@inproceedings{wang-etal-2021-input,
title = "Input Representations for Parsing Discourse Representation Structures: Comparing {E}nglish with {C}hinese",
author = "Wang, Chunliu and
van Noord, Rik and
Bisazza, Arianna and
Bos, Johan",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.97",
doi = "10.18653/v1/2021.acl-short.97",
pages = "767--775",
abstract = "Neural semantic parsers have obtained acceptable results in the context of parsing DRSs (Discourse Representation Structures). In particular models with character sequences as input showed remarkable performance for English. But how does this approach perform on languages with a different writing system, like Chinese, a language with a large vocabulary of characters? Does rule-based tokenisation of the input help, and which granularity is preferred: characters, or words? The results are promising. Even with DRSs based on English, good results for Chinese are obtained. Tokenisation offers a small advantage for English, but not for Chinese. Overall, characters are preferred as input, both for English and Chinese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-input">
<titleInfo>
<title>Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunliu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rik</namePart>
<namePart type="family">van Noord</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Bos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</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>Neural semantic parsers have obtained acceptable results in the context of parsing DRSs (Discourse Representation Structures). In particular models with character sequences as input showed remarkable performance for English. But how does this approach perform on languages with a different writing system, like Chinese, a language with a large vocabulary of characters? Does rule-based tokenisation of the input help, and which granularity is preferred: characters, or words? The results are promising. Even with DRSs based on English, good results for Chinese are obtained. Tokenisation offers a small advantage for English, but not for Chinese. Overall, characters are preferred as input, both for English and Chinese.</abstract>
<identifier type="citekey">wang-etal-2021-input</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.97</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.97</url>
</location>
<part>
<date>2021-aug</date>
<extent unit="page">
<start>767</start>
<end>775</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese
%A Wang, Chunliu
%A van Noord, Rik
%A Bisazza, Arianna
%A Bos, Johan
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-input
%X Neural semantic parsers have obtained acceptable results in the context of parsing DRSs (Discourse Representation Structures). In particular models with character sequences as input showed remarkable performance for English. But how does this approach perform on languages with a different writing system, like Chinese, a language with a large vocabulary of characters? Does rule-based tokenisation of the input help, and which granularity is preferred: characters, or words? The results are promising. Even with DRSs based on English, good results for Chinese are obtained. Tokenisation offers a small advantage for English, but not for Chinese. Overall, characters are preferred as input, both for English and Chinese.
%R 10.18653/v1/2021.acl-short.97
%U https://aclanthology.org/2021.acl-short.97
%U https://doi.org/10.18653/v1/2021.acl-short.97
%P 767-775
Markdown (Informal)
[Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese](https://aclanthology.org/2021.acl-short.97) (Wang et al., ACL 2021)
ACL