@inproceedings{liu-etal-2019-multi-lingual,
title = "Multi-lingual {W}ikipedia Summarization and Title Generation On Low Resource Corpus",
author = "Liu, Wei and
Li, Lei and
Huang, Zuying and
Liu, Yinan",
editor = "Giannakopoulos, George",
booktitle = "Proceedings of the Workshop MultiLing 2019: Summarization Across Languages, Genres and Sources",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/W19-8904",
doi = "10.26615/978-954-452-058-8_004",
pages = "17--25",
abstract = "MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus. In this paper we proposed QDAS extractive summarization model enhanced by sentence2vec and try to apply transfer learning based on large multilingual pre-trained language model for Wikipedia Headline Generation task. We treat it as sequence labeling task and develop two schemes to handle with it. Experimental results have shown that large pre-trained model can effectively utilize learned knowledge to extract certain phrase using low resource supervised data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2019-multi-lingual">
<titleInfo>
<title>Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuying</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop MultiLing 2019: Summarization Across Languages, Genres and Sources</title>
</titleInfo>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Giannakopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus. In this paper we proposed QDAS extractive summarization model enhanced by sentence2vec and try to apply transfer learning based on large multilingual pre-trained language model for Wikipedia Headline Generation task. We treat it as sequence labeling task and develop two schemes to handle with it. Experimental results have shown that large pre-trained model can effectively utilize learned knowledge to extract certain phrase using low resource supervised data.</abstract>
<identifier type="citekey">liu-etal-2019-multi-lingual</identifier>
<identifier type="doi">10.26615/978-954-452-058-8_004</identifier>
<location>
<url>https://aclanthology.org/W19-8904</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>17</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus
%A Liu, Wei
%A Li, Lei
%A Huang, Zuying
%A Liu, Yinan
%Y Giannakopoulos, George
%S Proceedings of the Workshop MultiLing 2019: Summarization Across Languages, Genres and Sources
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F liu-etal-2019-multi-lingual
%X MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus. In this paper we proposed QDAS extractive summarization model enhanced by sentence2vec and try to apply transfer learning based on large multilingual pre-trained language model for Wikipedia Headline Generation task. We treat it as sequence labeling task and develop two schemes to handle with it. Experimental results have shown that large pre-trained model can effectively utilize learned knowledge to extract certain phrase using low resource supervised data.
%R 10.26615/978-954-452-058-8_004
%U https://aclanthology.org/W19-8904
%U https://doi.org/10.26615/978-954-452-058-8_004
%P 17-25
Markdown (Informal)
[Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus](https://aclanthology.org/W19-8904) (Liu et al., RANLP 2019)
ACL