@inproceedings{zhang-etal-2020-ir,
title = "{IR}{\&}{TM}-{NJUST}@{CLS}ci{S}umm 20",
author = "Zhang, Heng and
Liu, Lifan and
Wang, Ruping and
Hu, Shaohu and
Ma, Shutian and
Zhang, Chengzhi",
booktitle = "Proceedings of the First Workshop on Scholarly Document Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sdp-1.33",
doi = "10.18653/v1/2020.sdp-1.33",
pages = "288--296",
abstract = "This paper mainly introduces our methods for Task 1A and Task 1B of CL-SciSumm 2020. Task 1A is to identify reference text in reference paper. Traditional machine learning models and MLP model are used. We evaluate the performances of these models and submit the final results from the optimal model. Compared with previous work, we optimize the ratio of positive to negative examples after data sampling. In order to construct features for classification, we calculate similarities between reference text and candidate sentences based on sentence vectors. Accordingly, nine similarities are used, of which eight are chosen from what we used in CL-SciSumm 2019 and a new sentence similarity based on fastText is added. Task 1B is to classify the facets of reference text. Unlike the methods used in CL-SciSumm 2019, we construct inputs of models based on word vectors and add deep learning models for classification this year.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2020-ir">
<titleInfo>
<title>IR&TM-NJUST@CLSciSumm 20</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruping</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaohu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shutian</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengzhi</namePart>
<namePart type="family">Zhang</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 First Workshop on Scholarly Document Processing</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 mainly introduces our methods for Task 1A and Task 1B of CL-SciSumm 2020. Task 1A is to identify reference text in reference paper. Traditional machine learning models and MLP model are used. We evaluate the performances of these models and submit the final results from the optimal model. Compared with previous work, we optimize the ratio of positive to negative examples after data sampling. In order to construct features for classification, we calculate similarities between reference text and candidate sentences based on sentence vectors. Accordingly, nine similarities are used, of which eight are chosen from what we used in CL-SciSumm 2019 and a new sentence similarity based on fastText is added. Task 1B is to classify the facets of reference text. Unlike the methods used in CL-SciSumm 2019, we construct inputs of models based on word vectors and add deep learning models for classification this year.</abstract>
<identifier type="citekey">zhang-etal-2020-ir</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.33</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.33</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>288</start>
<end>296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IR&TM-NJUST@CLSciSumm 20
%A Zhang, Heng
%A Liu, Lifan
%A Wang, Ruping
%A Hu, Shaohu
%A Ma, Shutian
%A Zhang, Chengzhi
%S Proceedings of the First Workshop on Scholarly Document Processing
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2020-ir
%X This paper mainly introduces our methods for Task 1A and Task 1B of CL-SciSumm 2020. Task 1A is to identify reference text in reference paper. Traditional machine learning models and MLP model are used. We evaluate the performances of these models and submit the final results from the optimal model. Compared with previous work, we optimize the ratio of positive to negative examples after data sampling. In order to construct features for classification, we calculate similarities between reference text and candidate sentences based on sentence vectors. Accordingly, nine similarities are used, of which eight are chosen from what we used in CL-SciSumm 2019 and a new sentence similarity based on fastText is added. Task 1B is to classify the facets of reference text. Unlike the methods used in CL-SciSumm 2019, we construct inputs of models based on word vectors and add deep learning models for classification this year.
%R 10.18653/v1/2020.sdp-1.33
%U https://aclanthology.org/2020.sdp-1.33
%U https://doi.org/10.18653/v1/2020.sdp-1.33
%P 288-296
Markdown (Informal)
[IR&TM-NJUST@CLSciSumm 20](https://aclanthology.org/2020.sdp-1.33) (Zhang et al., sdp 2020)
ACL
- Heng Zhang, Lifan Liu, Ruping Wang, Shaohu Hu, Shutian Ma, and Chengzhi Zhang. 2020. IR&TM-NJUST@CLSciSumm 20. In Proceedings of the First Workshop on Scholarly Document Processing, pages 288–296, Online. Association for Computational Linguistics.