@inproceedings{gupta-etal-2020-unified,
title = "A Unified Framework for Multilingual and Code-Mixed Visual Question Answering",
author = "Gupta, Deepak and
Lenka, Pabitra and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.90",
pages = "900--913",
abstract = "In this paper, we propose an effective deep learning framework for multilingual and code- mixed visual question answering. The pro- posed model is capable of predicting answers from the questions in Hindi, English or Code- mixed (Hinglish: Hindi-English) languages. The majority of the existing techniques on Vi- sual Question Answering (VQA) focus on En- glish questions only. However, many applica- tions such as medical imaging, tourism, visual assistants require a multilinguality-enabled module for their widespread usages. As there is no available dataset in English-Hindi VQA, we firstly create Hindi and Code-mixed VQA datasets by exploiting the linguistic properties of these languages. We propose a robust tech- nique capable of handling the multilingual and code-mixed question to provide the answer against the visual information (image). To better encode the multilingual and code-mixed questions, we introduce a hierarchy of shared layers. We control the behaviour of these shared layers by an attention-based soft layer sharing mechanism, which learns how shared layers are applied in different ways for the dif- ferent languages of the question. Further, our model uses bi-linear attention with a residual connection to fuse the language and image fea- tures. We perform extensive evaluation and ablation studies for English, Hindi and Code- mixed VQA. The evaluation shows that the proposed multilingual model achieves state-of- the-art performance in all these settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2020-unified">
<titleInfo>
<title>A Unified Framework for Multilingual and Code-Mixed Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pabitra</namePart>
<namePart type="family">Lenka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose an effective deep learning framework for multilingual and code- mixed visual question answering. The pro- posed model is capable of predicting answers from the questions in Hindi, English or Code- mixed (Hinglish: Hindi-English) languages. The majority of the existing techniques on Vi- sual Question Answering (VQA) focus on En- glish questions only. However, many applica- tions such as medical imaging, tourism, visual assistants require a multilinguality-enabled module for their widespread usages. As there is no available dataset in English-Hindi VQA, we firstly create Hindi and Code-mixed VQA datasets by exploiting the linguistic properties of these languages. We propose a robust tech- nique capable of handling the multilingual and code-mixed question to provide the answer against the visual information (image). To better encode the multilingual and code-mixed questions, we introduce a hierarchy of shared layers. We control the behaviour of these shared layers by an attention-based soft layer sharing mechanism, which learns how shared layers are applied in different ways for the dif- ferent languages of the question. Further, our model uses bi-linear attention with a residual connection to fuse the language and image fea- tures. We perform extensive evaluation and ablation studies for English, Hindi and Code- mixed VQA. The evaluation shows that the proposed multilingual model achieves state-of- the-art performance in all these settings.</abstract>
<identifier type="citekey">gupta-etal-2020-unified</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.90</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>900</start>
<end>913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Framework for Multilingual and Code-Mixed Visual Question Answering
%A Gupta, Deepak
%A Lenka, Pabitra
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F gupta-etal-2020-unified
%X In this paper, we propose an effective deep learning framework for multilingual and code- mixed visual question answering. The pro- posed model is capable of predicting answers from the questions in Hindi, English or Code- mixed (Hinglish: Hindi-English) languages. The majority of the existing techniques on Vi- sual Question Answering (VQA) focus on En- glish questions only. However, many applica- tions such as medical imaging, tourism, visual assistants require a multilinguality-enabled module for their widespread usages. As there is no available dataset in English-Hindi VQA, we firstly create Hindi and Code-mixed VQA datasets by exploiting the linguistic properties of these languages. We propose a robust tech- nique capable of handling the multilingual and code-mixed question to provide the answer against the visual information (image). To better encode the multilingual and code-mixed questions, we introduce a hierarchy of shared layers. We control the behaviour of these shared layers by an attention-based soft layer sharing mechanism, which learns how shared layers are applied in different ways for the dif- ferent languages of the question. Further, our model uses bi-linear attention with a residual connection to fuse the language and image fea- tures. We perform extensive evaluation and ablation studies for English, Hindi and Code- mixed VQA. The evaluation shows that the proposed multilingual model achieves state-of- the-art performance in all these settings.
%U https://aclanthology.org/2020.aacl-main.90
%P 900-913
Markdown (Informal)
[A Unified Framework for Multilingual and Code-Mixed Visual Question Answering](https://aclanthology.org/2020.aacl-main.90) (Gupta et al., AACL 2020)
ACL
- Deepak Gupta, Pabitra Lenka, Asif Ekbal, and Pushpak Bhattacharyya. 2020. A Unified Framework for Multilingual and Code-Mixed Visual Question Answering. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 900–913, Suzhou, China. Association for Computational Linguistics.