@inproceedings{faisal-anastasopoulos-2021-investigating,
title = "Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering",
author = "Faisal, Fahim and
Anastasopoulos, Antonios",
editor = "Fisch, Adam and
Talmor, Alon and
Chen, Danqi and
Choi, Eunsol and
Seo, Minjoon and
Lewis, Patrick and
Jia, Robin and
Min, Sewon",
booktitle = "Proceedings of the 3rd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrqa-1.14",
doi = "10.18653/v1/2021.mrqa-1.14",
pages = "133--148",
abstract = "Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pretrained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc finetuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faisal-anastasopoulos-2021-investigating">
<titleInfo>
<title>Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahim</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pretrained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc finetuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.</abstract>
<identifier type="citekey">faisal-anastasopoulos-2021-investigating</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.14</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>133</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering
%A Faisal, Fahim
%A Anastasopoulos, Antonios
%Y Fisch, Adam
%Y Talmor, Alon
%Y Chen, Danqi
%Y Choi, Eunsol
%Y Seo, Minjoon
%Y Lewis, Patrick
%Y Jia, Robin
%Y Min, Sewon
%S Proceedings of the 3rd Workshop on Machine Reading for Question Answering
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F faisal-anastasopoulos-2021-investigating
%X Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pretrained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc finetuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.
%R 10.18653/v1/2021.mrqa-1.14
%U https://aclanthology.org/2021.mrqa-1.14
%U https://doi.org/10.18653/v1/2021.mrqa-1.14
%P 133-148
Markdown (Informal)
[Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering](https://aclanthology.org/2021.mrqa-1.14) (Faisal & Anastasopoulos, MRQA 2021)
ACL