@inproceedings{liu-etal-2020-ji,
title = "基于跨语言双语预训练及{B}i-{LSTM}的汉-越平行句对抽取方法({C}hinese-{V}ietnamese Parallel Sentence Pair Extraction Method Based on Cross-lingual Bilingual Pre-training and {B}i-{LSTM})",
author = "Liu, Chang and
Gao, Shengxiang and
Yu, Zhengtao and
Huang, Yuxin and
You, Congcong",
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-1.42/",
pages = "457--466",
language = "zho",
abstract = "汉越平行句对抽取是缓解汉越平行语料库数据稀缺的重要方法。平行句对抽取可转换为同一语义空间下的句子相似性分类任务,其核心在于双语语义空间对齐。传统语义空间对齐方法依赖于大规模的双语平行语料,越南语作为低资源语言获取大规模平行语料相对困难。针对这个问题本文提出一种利用种子词典进行跨语言双语预训练及Bi-LSTM(Bi-directional Long Short-Term Memory)的汉-越平行句对抽取方法。预训练中仅需要大量的汉越单语和一个汉越种子词典,通过利用汉越种子词典将汉越双语映射到公共语义空间进行词对齐。再利用Bi-LSTM和CNN(Convolutional Neural Networks)分别提取句子的全局特征和局部特征从而最大化表示汉-越句对之间的语义相关性。实验结果表明,本文模型在F1得分上提升7.1{\%},优于基线模型。"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2020-ji">
<titleInfo>
<title>基于跨语言双语预训练及Bi-LSTM的汉-越平行句对抽取方法(Chinese-Vietnamese Parallel Sentence Pair Extraction Method Based on Cross-lingual Bilingual Pre-training and Bi-LSTM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengxiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengtao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Congcong</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</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>汉越平行句对抽取是缓解汉越平行语料库数据稀缺的重要方法。平行句对抽取可转换为同一语义空间下的句子相似性分类任务,其核心在于双语语义空间对齐。传统语义空间对齐方法依赖于大规模的双语平行语料,越南语作为低资源语言获取大规模平行语料相对困难。针对这个问题本文提出一种利用种子词典进行跨语言双语预训练及Bi-LSTM(Bi-directional Long Short-Term Memory)的汉-越平行句对抽取方法。预训练中仅需要大量的汉越单语和一个汉越种子词典,通过利用汉越种子词典将汉越双语映射到公共语义空间进行词对齐。再利用Bi-LSTM和CNN(Convolutional Neural Networks)分别提取句子的全局特征和局部特征从而最大化表示汉-越句对之间的语义相关性。实验结果表明,本文模型在F1得分上提升7.1%,优于基线模型。</abstract>
<identifier type="citekey">liu-etal-2020-ji</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.42/</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>457</start>
<end>466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于跨语言双语预训练及Bi-LSTM的汉-越平行句对抽取方法(Chinese-Vietnamese Parallel Sentence Pair Extraction Method Based on Cross-lingual Bilingual Pre-training and Bi-LSTM)
%A Liu, Chang
%A Gao, Shengxiang
%A Yu, Zhengtao
%A Huang, Yuxin
%A You, Congcong
%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 zho
%F liu-etal-2020-ji
%X 汉越平行句对抽取是缓解汉越平行语料库数据稀缺的重要方法。平行句对抽取可转换为同一语义空间下的句子相似性分类任务,其核心在于双语语义空间对齐。传统语义空间对齐方法依赖于大规模的双语平行语料,越南语作为低资源语言获取大规模平行语料相对困难。针对这个问题本文提出一种利用种子词典进行跨语言双语预训练及Bi-LSTM(Bi-directional Long Short-Term Memory)的汉-越平行句对抽取方法。预训练中仅需要大量的汉越单语和一个汉越种子词典,通过利用汉越种子词典将汉越双语映射到公共语义空间进行词对齐。再利用Bi-LSTM和CNN(Convolutional Neural Networks)分别提取句子的全局特征和局部特征从而最大化表示汉-越句对之间的语义相关性。实验结果表明,本文模型在F1得分上提升7.1%,优于基线模型。
%U https://aclanthology.org/2020.ccl-1.42/
%P 457-466
Markdown (Informal)
[基于跨语言双语预训练及Bi-LSTM的汉-越平行句对抽取方法(Chinese-Vietnamese Parallel Sentence Pair Extraction Method Based on Cross-lingual Bilingual Pre-training and Bi-LSTM)](https://aclanthology.org/2020.ccl-1.42/) (Liu et al., CCL 2020)
ACL