@inproceedings{trisedya-etal-2021-grouped-attention,
title = "Grouped-Attention for Content-Selection and Content-Plan Generation",
author = "Trisedya, Bayu Distiawan and
Wang, Xiaojie and
Qi, Jianzhong and
Zhang, Rui and
Cui, Qingjun",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.166",
doi = "10.18653/v1/2021.findings-emnlp.166",
pages = "1935--1944",
abstract = "Content-planning is an essential part of data-to-text generation to determine the order of data mentioned in generated texts. Recent neural data-to-text generation models employ Pointer Networks to explicitly learn content-plan given a set of attributes as input. They use LSTM to encode the input, which assumes a sequential relationship in the input. This may be sub-optimal to encode a set of attributes, where the attributes have a composite structure: the attributes are disordered while each attribute value is an ordered list of tokens. We handle this problem by proposing a neural content-planner that can capture both local and global contexts of such a structure. Specifically, we propose a novel attention mechanism called GSC-attention. A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context. Moreover, our content-planner explicitly learns content-selection, which is integrated into the content-planner to select the most important data to be included in the generated text via an attention masking procedure. Experimental results show that our model outperforms the competitors by 4.92{\%}, 4.70{\%}, and 16.56{\%} in terms of Damerau-Levenshtein Distance scores on three real-world datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trisedya-etal-2021-grouped-attention">
<titleInfo>
<title>Grouped-Attention for Content-Selection and Content-Plan Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bayu</namePart>
<namePart type="given">Distiawan</namePart>
<namePart type="family">Trisedya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianzhong</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingjun</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Content-planning is an essential part of data-to-text generation to determine the order of data mentioned in generated texts. Recent neural data-to-text generation models employ Pointer Networks to explicitly learn content-plan given a set of attributes as input. They use LSTM to encode the input, which assumes a sequential relationship in the input. This may be sub-optimal to encode a set of attributes, where the attributes have a composite structure: the attributes are disordered while each attribute value is an ordered list of tokens. We handle this problem by proposing a neural content-planner that can capture both local and global contexts of such a structure. Specifically, we propose a novel attention mechanism called GSC-attention. A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context. Moreover, our content-planner explicitly learns content-selection, which is integrated into the content-planner to select the most important data to be included in the generated text via an attention masking procedure. Experimental results show that our model outperforms the competitors by 4.92%, 4.70%, and 16.56% in terms of Damerau-Levenshtein Distance scores on three real-world datasets.</abstract>
<identifier type="citekey">trisedya-etal-2021-grouped-attention</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.166</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.166</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1935</start>
<end>1944</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grouped-Attention for Content-Selection and Content-Plan Generation
%A Trisedya, Bayu Distiawan
%A Wang, Xiaojie
%A Qi, Jianzhong
%A Zhang, Rui
%A Cui, Qingjun
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F trisedya-etal-2021-grouped-attention
%X Content-planning is an essential part of data-to-text generation to determine the order of data mentioned in generated texts. Recent neural data-to-text generation models employ Pointer Networks to explicitly learn content-plan given a set of attributes as input. They use LSTM to encode the input, which assumes a sequential relationship in the input. This may be sub-optimal to encode a set of attributes, where the attributes have a composite structure: the attributes are disordered while each attribute value is an ordered list of tokens. We handle this problem by proposing a neural content-planner that can capture both local and global contexts of such a structure. Specifically, we propose a novel attention mechanism called GSC-attention. A key component of the GSC-attention is grouped-attention, which is token-level attention constrained within each input attribute that enables our proposed model captures both local and global context. Moreover, our content-planner explicitly learns content-selection, which is integrated into the content-planner to select the most important data to be included in the generated text via an attention masking procedure. Experimental results show that our model outperforms the competitors by 4.92%, 4.70%, and 16.56% in terms of Damerau-Levenshtein Distance scores on three real-world datasets.
%R 10.18653/v1/2021.findings-emnlp.166
%U https://aclanthology.org/2021.findings-emnlp.166
%U https://doi.org/10.18653/v1/2021.findings-emnlp.166
%P 1935-1944
Markdown (Informal)
[Grouped-Attention for Content-Selection and Content-Plan Generation](https://aclanthology.org/2021.findings-emnlp.166) (Trisedya et al., Findings 2021)
ACL