@inproceedings{das-etal-2026-video,
title = "Video-guided Machine Translation for {I}ndic Languages",
author = "Das, Pinaki and
Ayyagari, Srikar and
Dabre, Raj and
Vu, Thuy-Trang and
Singh, Virendra and
Bhattacharyya, Pushpak and
Haffari, Gholamreza",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.57/",
pages = "1214--1235",
ISBN = "979-8-89176-439-2",
abstract = "Video-guided machine translation (VMT) translates text by leveraging the context provided by the accompanying video. This additional contextual information helps improve translation quality by disambiguating ambiguous words or explicitly indicating attributes such as the colour or gender of objects and people. Prior works have extensively explored VMT; however, most approaches train models from scratch, which requires large amounts of data. Additionally, the majority of VMT research has focused on the English{--}Chinese language pair. In this paper, we explore training strategies for VMT using only a limited amount of data and extend the task to Indic languages, specifically Hindi, Marathi and Odia. We also propose a synthetic data framework that is effective for training VMT models in low-resource language settings. Our results demonstrate an improvement of +1.75 BLEU compared to baseline models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2026-video">
<titleInfo>
<title>Video-guided Machine Translation for Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pinaki</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srikar</namePart>
<namePart type="family">Ayyagari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thuy-Trang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Virendra</namePart>
<namePart type="family">Singh</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>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Video-guided machine translation (VMT) translates text by leveraging the context provided by the accompanying video. This additional contextual information helps improve translation quality by disambiguating ambiguous words or explicitly indicating attributes such as the colour or gender of objects and people. Prior works have extensively explored VMT; however, most approaches train models from scratch, which requires large amounts of data. Additionally, the majority of VMT research has focused on the English–Chinese language pair. In this paper, we explore training strategies for VMT using only a limited amount of data and extend the task to Indic languages, specifically Hindi, Marathi and Odia. We also propose a synthetic data framework that is effective for training VMT models in low-resource language settings. Our results demonstrate an improvement of +1.75 BLEU compared to baseline models.</abstract>
<identifier type="citekey">das-etal-2026-video</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.57/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1214</start>
<end>1235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Video-guided Machine Translation for Indic Languages
%A Das, Pinaki
%A Ayyagari, Srikar
%A Dabre, Raj
%A Vu, Thuy-Trang
%A Singh, Virendra
%A Bhattacharyya, Pushpak
%A Haffari, Gholamreza
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F das-etal-2026-video
%X Video-guided machine translation (VMT) translates text by leveraging the context provided by the accompanying video. This additional contextual information helps improve translation quality by disambiguating ambiguous words or explicitly indicating attributes such as the colour or gender of objects and people. Prior works have extensively explored VMT; however, most approaches train models from scratch, which requires large amounts of data. Additionally, the majority of VMT research has focused on the English–Chinese language pair. In this paper, we explore training strategies for VMT using only a limited amount of data and extend the task to Indic languages, specifically Hindi, Marathi and Odia. We also propose a synthetic data framework that is effective for training VMT models in low-resource language settings. Our results demonstrate an improvement of +1.75 BLEU compared to baseline models.
%U https://aclanthology.org/2026.aacl-long.57/
%P 1214-1235
Markdown (Informal)
[Video-guided Machine Translation for Indic Languages](https://aclanthology.org/2026.aacl-long.57/) (Das et al., AACL-IJCNLP 2026)
ACL
- Pinaki Das, Srikar Ayyagari, Raj Dabre, Thuy-Trang Vu, Virendra Singh, Pushpak Bhattacharyya, and Gholamreza Haffari. 2026. Video-guided Machine Translation for Indic Languages. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1214–1235, Hengqin, China. Association for Computational Linguistics.