@inproceedings{roy-etal-2022-meta,
title = "Does Meta-learning Help m{BERT} for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?",
author = "Roy, Aniruddha and
Thakur, Rupak Kumar and
Sharma, Isha and
Gupta, Ashim and
Krishna, Amrith and
Sarkar, Sudeshna and
Goyal, Pawan",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.373",
pages = "4251--4257",
abstract = "Few-shot Question Generation (QG) is an important and challenging problem in the Natural Language Generation (NLG) domain. Multilingual BERT (mBERT) has been successfully used in various Natural Language Understanding (NLU) applications. However, the question of how to utilize mBERT for few-shot QG, possibly with cross-lingual transfer, remains. In this paper, we try to explore how mBERT performs in few-shot QG (cross-lingual transfer) and also whether applying meta-learning on mBERT further improves the results. In our setting, we consider mBERT as the base model and fine-tune it using a seq-to-seq language modeling framework in a cross-lingual setting. Further, we apply the model agnostic meta-learning approach to our base model. We evaluate our model for two low-resource Indian languages, Bengali and Telugu, using the TyDi QA dataset. The proposed approach consistently improves the performance of the base model in few-shot settings and even works better than some heavily parameterized models. Human evaluation also confirms the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-etal-2022-meta">
<titleInfo>
<title>Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aniruddha</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rupak</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Thakur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isha</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashim</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrith</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudeshna</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Few-shot Question Generation (QG) is an important and challenging problem in the Natural Language Generation (NLG) domain. Multilingual BERT (mBERT) has been successfully used in various Natural Language Understanding (NLU) applications. However, the question of how to utilize mBERT for few-shot QG, possibly with cross-lingual transfer, remains. In this paper, we try to explore how mBERT performs in few-shot QG (cross-lingual transfer) and also whether applying meta-learning on mBERT further improves the results. In our setting, we consider mBERT as the base model and fine-tune it using a seq-to-seq language modeling framework in a cross-lingual setting. Further, we apply the model agnostic meta-learning approach to our base model. We evaluate our model for two low-resource Indian languages, Bengali and Telugu, using the TyDi QA dataset. The proposed approach consistently improves the performance of the base model in few-shot settings and even works better than some heavily parameterized models. Human evaluation also confirms the effectiveness of our approach.</abstract>
<identifier type="citekey">roy-etal-2022-meta</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.373</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4251</start>
<end>4257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?
%A Roy, Aniruddha
%A Thakur, Rupak Kumar
%A Sharma, Isha
%A Gupta, Ashim
%A Krishna, Amrith
%A Sarkar, Sudeshna
%A Goyal, Pawan
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F roy-etal-2022-meta
%X Few-shot Question Generation (QG) is an important and challenging problem in the Natural Language Generation (NLG) domain. Multilingual BERT (mBERT) has been successfully used in various Natural Language Understanding (NLU) applications. However, the question of how to utilize mBERT for few-shot QG, possibly with cross-lingual transfer, remains. In this paper, we try to explore how mBERT performs in few-shot QG (cross-lingual transfer) and also whether applying meta-learning on mBERT further improves the results. In our setting, we consider mBERT as the base model and fine-tune it using a seq-to-seq language modeling framework in a cross-lingual setting. Further, we apply the model agnostic meta-learning approach to our base model. We evaluate our model for two low-resource Indian languages, Bengali and Telugu, using the TyDi QA dataset. The proposed approach consistently improves the performance of the base model in few-shot settings and even works better than some heavily parameterized models. Human evaluation also confirms the effectiveness of our approach.
%U https://aclanthology.org/2022.coling-1.373
%P 4251-4257
Markdown (Informal)
[Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages?](https://aclanthology.org/2022.coling-1.373) (Roy et al., COLING 2022)
ACL