@inproceedings{feiyang-etal-2020-recognition,
title = "Recognition Method of Important Words in {K}orean Text based on Reinforcement Learning",
author = "Feiyang, Yang and
Yahui, Zhao and
Rongyi, Cui",
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-1.94",
pages = "1017--1025",
abstract = "The manual labeling work for constructing the Korean corpus is too time-consuming and laborious. It is difficult for low-minority languages to integrate resources. As a result, the research progress of Korean language information processing is slow. From the perspective of representation learning, reinforcement learning was combined with traditional deep learning methods. Based on the Korean text classification effect as a benchmark, and studied how to extract important Korean words in sentences. A structured model Information Distilled of Korean (IDK) was proposed. The model recognizes the words in Korean sentences and retains important words and deletes non-important words. Thereby transforming the reconstruction of the sentence into a sequential decision problem. So you can introduce the Policy Gradient method in reinforcement learning to solve the conversion problem. The results show that the model can identify the important words in Korean instead of manual annotation for representation learning. Furthermore, compared with traditional text classification methods, the model also improves the effect of Korean text classification.",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feiyang-etal-2020-recognition">
<titleInfo>
<title>Recognition Method of Important Words in Korean Text based on Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feiyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Yahui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cui</namePart>
<namePart type="family">Rongyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</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>
<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>The manual labeling work for constructing the Korean corpus is too time-consuming and laborious. It is difficult for low-minority languages to integrate resources. As a result, the research progress of Korean language information processing is slow. From the perspective of representation learning, reinforcement learning was combined with traditional deep learning methods. Based on the Korean text classification effect as a benchmark, and studied how to extract important Korean words in sentences. A structured model Information Distilled of Korean (IDK) was proposed. The model recognizes the words in Korean sentences and retains important words and deletes non-important words. Thereby transforming the reconstruction of the sentence into a sequential decision problem. So you can introduce the Policy Gradient method in reinforcement learning to solve the conversion problem. The results show that the model can identify the important words in Korean instead of manual annotation for representation learning. Furthermore, compared with traditional text classification methods, the model also improves the effect of Korean text classification.</abstract>
<identifier type="citekey">feiyang-etal-2020-recognition</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.94</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>1017</start>
<end>1025</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recognition Method of Important Words in Korean Text based on Reinforcement Learning
%A Feiyang, Yang
%A Yahui, Zhao
%A Rongyi, Cui
%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 English
%F feiyang-etal-2020-recognition
%X The manual labeling work for constructing the Korean corpus is too time-consuming and laborious. It is difficult for low-minority languages to integrate resources. As a result, the research progress of Korean language information processing is slow. From the perspective of representation learning, reinforcement learning was combined with traditional deep learning methods. Based on the Korean text classification effect as a benchmark, and studied how to extract important Korean words in sentences. A structured model Information Distilled of Korean (IDK) was proposed. The model recognizes the words in Korean sentences and retains important words and deletes non-important words. Thereby transforming the reconstruction of the sentence into a sequential decision problem. So you can introduce the Policy Gradient method in reinforcement learning to solve the conversion problem. The results show that the model can identify the important words in Korean instead of manual annotation for representation learning. Furthermore, compared with traditional text classification methods, the model also improves the effect of Korean text classification.
%U https://aclanthology.org/2020.ccl-1.94
%P 1017-1025
Markdown (Informal)
[Recognition Method of Important Words in Korean Text based on Reinforcement Learning](https://aclanthology.org/2020.ccl-1.94) (Feiyang et al., CCL 2020)
ACL