@inproceedings{guan-etal-2020-refining,
title = "Refining Data for Text Generation",
author = "Liu, Qianying and
Li, Tianyi and
Guan, Wenyu and
Li, Sujian",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
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-1.82/",
pages = "881--891",
language = "eng",
abstract = "Recent work on data-to-text generation has made progress under the neural encoder-decoder architectures. However, the data input size is often enormous, while not all data records are important for text generation and inappropriate input may bring noise into the final output. To solve this problem, we propose a two-step approach which first selects and orders the important data records and then generates text from the noise-reduced data. Here we propose a learning to rank model to rank the importance of each record which is supervised by a relation extractor. With the noise-reduced data as input, we implement a text generator which sequentially models the input data records and emits a summary. Experiments on the ROTOWIRE dataset verifies the effectiveness of our proposed method in both performance and efficiency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2020-refining">
<titleInfo>
<title>Refining Data for Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianying</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Recent work on data-to-text generation has made progress under the neural encoder-decoder architectures. However, the data input size is often enormous, while not all data records are important for text generation and inappropriate input may bring noise into the final output. To solve this problem, we propose a two-step approach which first selects and orders the important data records and then generates text from the noise-reduced data. Here we propose a learning to rank model to rank the importance of each record which is supervised by a relation extractor. With the noise-reduced data as input, we implement a text generator which sequentially models the input data records and emits a summary. Experiments on the ROTOWIRE dataset verifies the effectiveness of our proposed method in both performance and efficiency.</abstract>
<identifier type="citekey">guan-etal-2020-refining</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.82/</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>881</start>
<end>891</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refining Data for Text Generation
%A Liu, Qianying
%A Li, Tianyi
%A Guan, Wenyu
%A Li, Sujian
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G eng
%F guan-etal-2020-refining
%X Recent work on data-to-text generation has made progress under the neural encoder-decoder architectures. However, the data input size is often enormous, while not all data records are important for text generation and inappropriate input may bring noise into the final output. To solve this problem, we propose a two-step approach which first selects and orders the important data records and then generates text from the noise-reduced data. Here we propose a learning to rank model to rank the importance of each record which is supervised by a relation extractor. With the noise-reduced data as input, we implement a text generator which sequentially models the input data records and emits a summary. Experiments on the ROTOWIRE dataset verifies the effectiveness of our proposed method in both performance and efficiency.
%U https://aclanthology.org/2020.ccl-1.82/
%P 881-891
Markdown (Informal)
[Refining Data for Text Generation](https://aclanthology.org/2020.ccl-1.82/) (Liu et al., CCL 2020)
ACL
- Qianying Liu, Tianyi Li, Wenyu Guan, and Sujian Li. 2020. Refining Data for Text Generation. In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 881–891, Haikou, China. Chinese Information Processing Society of China.