@inproceedings{kolluru-etal-2022-alignment,
title = "Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction",
author = "Kolluru, Keshav and
Mohammed, Muqeeth and
Mittal, Shubham and
Chakrabarti, Soumen and
{Mausam}",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.179",
doi = "10.18653/v1/2022.acl-long.179",
pages = "2502--2517",
abstract = "Progress with supervised Open Information Extraction (OpenIE) has been primarily limited to English due to the scarcity of training data in other languages. In this paper, we explore techniques to automatically convert English text for training OpenIE systems in other languages. We introduce the Alignment-Augmented Constrained Translation (AACTrans) model to translate English sentences and their corresponding extractions consistently with each other {---} with no changes to vocabulary or semantic meaning which may result from independent translations. Using the data generated with AACTrans, we train a novel two-stage generative OpenIE model, which we call Gen2OIE, that outputs for each sentence: 1) relations in the first stage and 2) all extractions containing the relation in the second stage. Gen2OIE increases relation coverage using a training data transformation technique that is generalizable to multiple languages, in contrast to existing models that use an English-specific training loss. Evaluations on 5 languages {---} Spanish, Portuguese, Chinese, Hindi and Telugu {---} show that the Gen2OIE with AACTrans data outperforms prior systems by a margin of 6-25{\%} in F1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolluru-etal-2022-alignment">
<titleInfo>
<title>Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keshav</namePart>
<namePart type="family">Kolluru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muqeeth</namePart>
<namePart type="family">Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Chakrabarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Progress with supervised Open Information Extraction (OpenIE) has been primarily limited to English due to the scarcity of training data in other languages. In this paper, we explore techniques to automatically convert English text for training OpenIE systems in other languages. We introduce the Alignment-Augmented Constrained Translation (AACTrans) model to translate English sentences and their corresponding extractions consistently with each other — with no changes to vocabulary or semantic meaning which may result from independent translations. Using the data generated with AACTrans, we train a novel two-stage generative OpenIE model, which we call Gen2OIE, that outputs for each sentence: 1) relations in the first stage and 2) all extractions containing the relation in the second stage. Gen2OIE increases relation coverage using a training data transformation technique that is generalizable to multiple languages, in contrast to existing models that use an English-specific training loss. Evaluations on 5 languages — Spanish, Portuguese, Chinese, Hindi and Telugu — show that the Gen2OIE with AACTrans data outperforms prior systems by a margin of 6-25% in F1.</abstract>
<identifier type="citekey">kolluru-etal-2022-alignment</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.179</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.179</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2502</start>
<end>2517</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction
%A Kolluru, Keshav
%A Mohammed, Muqeeth
%A Mittal, Shubham
%A Chakrabarti, Soumen
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%A Mausam
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kolluru-etal-2022-alignment
%X Progress with supervised Open Information Extraction (OpenIE) has been primarily limited to English due to the scarcity of training data in other languages. In this paper, we explore techniques to automatically convert English text for training OpenIE systems in other languages. We introduce the Alignment-Augmented Constrained Translation (AACTrans) model to translate English sentences and their corresponding extractions consistently with each other — with no changes to vocabulary or semantic meaning which may result from independent translations. Using the data generated with AACTrans, we train a novel two-stage generative OpenIE model, which we call Gen2OIE, that outputs for each sentence: 1) relations in the first stage and 2) all extractions containing the relation in the second stage. Gen2OIE increases relation coverage using a training data transformation technique that is generalizable to multiple languages, in contrast to existing models that use an English-specific training loss. Evaluations on 5 languages — Spanish, Portuguese, Chinese, Hindi and Telugu — show that the Gen2OIE with AACTrans data outperforms prior systems by a margin of 6-25% in F1.
%R 10.18653/v1/2022.acl-long.179
%U https://aclanthology.org/2022.acl-long.179
%U https://doi.org/10.18653/v1/2022.acl-long.179
%P 2502-2517
Markdown (Informal)
[Alignment-Augmented Consistent Translation for Multilingual Open Information Extraction](https://aclanthology.org/2022.acl-long.179) (Kolluru et al., ACL 2022)
ACL