@inproceedings{yancui-etal-2020-chinese,
title = "{C}hinese and {E}nglish Elementary Discourse Units Segmentation based on {B}i-{LSTM}-{CRF} Model",
author = "Yancui, Li and
Chunxiao, Lai and
Jike, Feng and
Hongyu, Feng",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.99",
pages = "1068--1078",
abstract = "Elementary Discourse Unit (EDU) recognition is the basic task of discourse analysis, and the Chinese and English discourse alignment corpus is helpful to the studies of EDU recognition. This paper first builds Chinese-English parallel discourse corpus, in which EDUs are annotated and aligned. Then, we present the framework of Bi-LSTM-CRF EDUs recognition model using word embedding, POS and syntactic features, which can combine the advantage of CRF and Bi-LSTM. The results show that F1 is about 2{\%} higher than the traditional method. Compared with CRF and Bi-LSTM, the Bi-LSTM-CRF model can combine the advantages of them and obtains satisfactory results for Chinese and English EDUs recognition. The experiment of feature contribution shows that using all features together can get best result, the syntactic feature outperforms than other features.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yancui-etal-2020-chinese">
<titleInfo>
<title>Chinese and English Elementary Discourse Units Segmentation based on Bi-LSTM-CRF Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Yancui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lai</namePart>
<namePart type="family">Chunxiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Jike</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Hongyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Elementary Discourse Unit (EDU) recognition is the basic task of discourse analysis, and the Chinese and English discourse alignment corpus is helpful to the studies of EDU recognition. This paper first builds Chinese-English parallel discourse corpus, in which EDUs are annotated and aligned. Then, we present the framework of Bi-LSTM-CRF EDUs recognition model using word embedding, POS and syntactic features, which can combine the advantage of CRF and Bi-LSTM. The results show that F1 is about 2% higher than the traditional method. Compared with CRF and Bi-LSTM, the Bi-LSTM-CRF model can combine the advantages of them and obtains satisfactory results for Chinese and English EDUs recognition. The experiment of feature contribution shows that using all features together can get best result, the syntactic feature outperforms than other features.</abstract>
<identifier type="citekey">yancui-etal-2020-chinese</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.99</url>
</location>
<part>
<date>2020-oct</date>
<extent unit="page">
<start>1068</start>
<end>1078</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese and English Elementary Discourse Units Segmentation based on Bi-LSTM-CRF Model
%A Yancui, Li
%A Chunxiao, Lai
%A Jike, Feng
%A Hongyu, Feng
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 oct
%I Chinese Information Processing Society of China
%C Haikou, China
%G English
%F yancui-etal-2020-chinese
%X Elementary Discourse Unit (EDU) recognition is the basic task of discourse analysis, and the Chinese and English discourse alignment corpus is helpful to the studies of EDU recognition. This paper first builds Chinese-English parallel discourse corpus, in which EDUs are annotated and aligned. Then, we present the framework of Bi-LSTM-CRF EDUs recognition model using word embedding, POS and syntactic features, which can combine the advantage of CRF and Bi-LSTM. The results show that F1 is about 2% higher than the traditional method. Compared with CRF and Bi-LSTM, the Bi-LSTM-CRF model can combine the advantages of them and obtains satisfactory results for Chinese and English EDUs recognition. The experiment of feature contribution shows that using all features together can get best result, the syntactic feature outperforms than other features.
%U https://aclanthology.org/2020.ccl-1.99
%P 1068-1078
Markdown (Informal)
[Chinese and English Elementary Discourse Units Segmentation based on Bi-LSTM-CRF Model](https://aclanthology.org/2020.ccl-1.99) (Yancui et al., CCL 2020)
ACL