@inproceedings{zhao-etal-2020-knowledge,
title = "Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity",
author = "Zhao, Yang and
Xiang, Lu and
Zhu, Junnan and
Zhang, Jiajun and
Zhou, Yu and
Zong, Chengqing",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.397/",
doi = "10.18653/v1/2020.coling-main.397",
pages = "4495--4505",
abstract = "Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismatch: the current KG methods utilize the entity as the basic granularity, while NMT utilizes the sub-word as the granularity, making the KG different to be utilized in NMT. To alleviate above problems, we propose a multi-task learning method on sub-entity granularity. Specifically, we first split the entities in KG and sentence pairs into sub-entity granularity by using joint BPE. Then we utilize the multi-task learning to combine the machine translation task and knowledge reasoning task. The extensive experiments on various translation tasks have demonstrated that our method significantly outperforms the baseline models in both translation quality and handling the entities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2020-knowledge">
<titleInfo>
<title>Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismatch: the current KG methods utilize the entity as the basic granularity, while NMT utilizes the sub-word as the granularity, making the KG different to be utilized in NMT. To alleviate above problems, we propose a multi-task learning method on sub-entity granularity. Specifically, we first split the entities in KG and sentence pairs into sub-entity granularity by using joint BPE. Then we utilize the multi-task learning to combine the machine translation task and knowledge reasoning task. The extensive experiments on various translation tasks have demonstrated that our method significantly outperforms the baseline models in both translation quality and handling the entities.</abstract>
<identifier type="citekey">zhao-etal-2020-knowledge</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.397</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.397/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4495</start>
<end>4505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity
%A Zhao, Yang
%A Xiang, Lu
%A Zhu, Junnan
%A Zhang, Jiajun
%A Zhou, Yu
%A Zong, Chengqing
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F zhao-etal-2020-knowledge
%X Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized. ii) Granularity mismatch: the current KG methods utilize the entity as the basic granularity, while NMT utilizes the sub-word as the granularity, making the KG different to be utilized in NMT. To alleviate above problems, we propose a multi-task learning method on sub-entity granularity. Specifically, we first split the entities in KG and sentence pairs into sub-entity granularity by using joint BPE. Then we utilize the multi-task learning to combine the machine translation task and knowledge reasoning task. The extensive experiments on various translation tasks have demonstrated that our method significantly outperforms the baseline models in both translation quality and handling the entities.
%R 10.18653/v1/2020.coling-main.397
%U https://aclanthology.org/2020.coling-main.397/
%U https://doi.org/10.18653/v1/2020.coling-main.397
%P 4495-4505
Markdown (Informal)
[Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity](https://aclanthology.org/2020.coling-main.397/) (Zhao et al., COLING 2020)
ACL