@inproceedings{nath-etal-2022-image,
title = "Image Caption Generation for Low-Resource {A}ssamese Language",
author = "Nath, Prachurya and
Adhikary, Prottay Kumar and
Dadure, Pankaj and
Pakray, Partha and
Manna, Riyanka and
Bandyopadhyay, Sivaji",
editor = "Chang, Yung-Chun and
Huang, Yi-Chin",
booktitle = "Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)",
month = nov,
year = "2022",
address = "Taipei, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2022.rocling-1.33",
pages = "263--272",
abstract = "Image captioning is a prominent Artificial Intelligence (AI) research area that deals with visual recognition and a linguistic description of the image. It is an interdisciplinary field concerning how computers can see and understand digital images{\&} videos, and describe them in a language known to humans. Constructing a meaningful sentence needs both structural and semantic information of the language. This paper highlights the contribution of image caption generation for the Assamese language. The unavailability of an image caption generation system for the Assamese language is an open problem for AI-NLP researchers, and it{'}s just an early stage of the research. To achieve our defined objective, we have used the encoder-decoder framework, which combines the Convolutional Neural Networks and the Recurrent Neural Networks. The experiment has been tested on Flickr30k and Coco Captions dataset, which have been originally present in the English language. We have translated these datasets into Assamese language using the state-of-the-art Machine Translation (MT) system for our designed work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nath-etal-2022-image">
<titleInfo>
<title>Image Caption Generation for Low-Resource Assamese Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prachurya</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prottay</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Adhikary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pankaj</namePart>
<namePart type="family">Dadure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Partha</namePart>
<namePart type="family">Pakray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riyanka</namePart>
<namePart type="family">Manna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yung-Chun</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Chin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Image captioning is a prominent Artificial Intelligence (AI) research area that deals with visual recognition and a linguistic description of the image. It is an interdisciplinary field concerning how computers can see and understand digital images& videos, and describe them in a language known to humans. Constructing a meaningful sentence needs both structural and semantic information of the language. This paper highlights the contribution of image caption generation for the Assamese language. The unavailability of an image caption generation system for the Assamese language is an open problem for AI-NLP researchers, and it’s just an early stage of the research. To achieve our defined objective, we have used the encoder-decoder framework, which combines the Convolutional Neural Networks and the Recurrent Neural Networks. The experiment has been tested on Flickr30k and Coco Captions dataset, which have been originally present in the English language. We have translated these datasets into Assamese language using the state-of-the-art Machine Translation (MT) system for our designed work.</abstract>
<identifier type="citekey">nath-etal-2022-image</identifier>
<location>
<url>https://aclanthology.org/2022.rocling-1.33</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>263</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Image Caption Generation for Low-Resource Assamese Language
%A Nath, Prachurya
%A Adhikary, Prottay Kumar
%A Dadure, Pankaj
%A Pakray, Partha
%A Manna, Riyanka
%A Bandyopadhyay, Sivaji
%Y Chang, Yung-Chun
%Y Huang, Yi-Chin
%S Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)
%D 2022
%8 November
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taipei, Taiwan
%F nath-etal-2022-image
%X Image captioning is a prominent Artificial Intelligence (AI) research area that deals with visual recognition and a linguistic description of the image. It is an interdisciplinary field concerning how computers can see and understand digital images& videos, and describe them in a language known to humans. Constructing a meaningful sentence needs both structural and semantic information of the language. This paper highlights the contribution of image caption generation for the Assamese language. The unavailability of an image caption generation system for the Assamese language is an open problem for AI-NLP researchers, and it’s just an early stage of the research. To achieve our defined objective, we have used the encoder-decoder framework, which combines the Convolutional Neural Networks and the Recurrent Neural Networks. The experiment has been tested on Flickr30k and Coco Captions dataset, which have been originally present in the English language. We have translated these datasets into Assamese language using the state-of-the-art Machine Translation (MT) system for our designed work.
%U https://aclanthology.org/2022.rocling-1.33
%P 263-272
Markdown (Informal)
[Image Caption Generation for Low-Resource Assamese Language](https://aclanthology.org/2022.rocling-1.33) (Nath et al., ROCLING 2022)
ACL
- Prachurya Nath, Prottay Kumar Adhikary, Pankaj Dadure, Partha Pakray, Riyanka Manna, and Sivaji Bandyopadhyay. 2022. Image Caption Generation for Low-Resource Assamese Language. In Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022), pages 263–272, Taipei, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).