@inproceedings{terdalkar-bhattacharya-2023-antarlekhaka,
title = "Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation",
author = "Terdalkar, Hrishikesh and
Bhattacharya, Arnab",
editor = "Tan, Liling and
Milajevs, Dmitrijs and
Chauhan, Geeticka and
Gwinnup, Jeremy and
Rippeth, Elijah",
booktitle = "Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlposs-1.23/",
doi = "10.18653/v1/2023.nlposs-1.23",
pages = "199--211",
abstract = "One of the primary obstacles in the advancement of Natural Language Processing (NLP) technologies for low-resource languages is the lack of annotated datasets for training and testing machine learning models. In this paper, we present \textit{Antarlekhaka}, a tool for manual annotation of a comprehensive set of tasks relevant to NLP. The tool is Unicode-compatible, language-agnostic, Web-deployable and supports distributed annotation by multiple simultaneous annotators. The system sports user-friendly interfaces for 8 categories of annotation tasks. These, in turn, enable the annotation of a considerably larger set of NLP tasks. The task categories include two linguistic tasks not handled by any other tool, namely, sentence boundary detection and deciding canonical word order, which are important tasks for text that is in the form of poetry. We propose the idea of \textit{sequential annotation} based on small text units, where an annotator performs several tasks related to a single text unit before proceeding to the next unit. The research applications of the proposed mode of multi-task annotation are also discussed. Antarlekhaka outperforms other annotation tools in objective evaluation. It has been also used for two real-life annotation tasks on two different languages, namely, Sanskrit and Bengali. The tool is available at \url{https://github.com/Antarlekhaka/code}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="terdalkar-bhattacharya-2023-antarlekhaka">
<titleInfo>
<title>Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hrishikesh</namePart>
<namePart type="family">Terdalkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elijah</namePart>
<namePart type="family">Rippeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the primary obstacles in the advancement of Natural Language Processing (NLP) technologies for low-resource languages is the lack of annotated datasets for training and testing machine learning models. In this paper, we present Antarlekhaka, a tool for manual annotation of a comprehensive set of tasks relevant to NLP. The tool is Unicode-compatible, language-agnostic, Web-deployable and supports distributed annotation by multiple simultaneous annotators. The system sports user-friendly interfaces for 8 categories of annotation tasks. These, in turn, enable the annotation of a considerably larger set of NLP tasks. The task categories include two linguistic tasks not handled by any other tool, namely, sentence boundary detection and deciding canonical word order, which are important tasks for text that is in the form of poetry. We propose the idea of sequential annotation based on small text units, where an annotator performs several tasks related to a single text unit before proceeding to the next unit. The research applications of the proposed mode of multi-task annotation are also discussed. Antarlekhaka outperforms other annotation tools in objective evaluation. It has been also used for two real-life annotation tasks on two different languages, namely, Sanskrit and Bengali. The tool is available at https://github.com/Antarlekhaka/code</abstract>
<identifier type="citekey">terdalkar-bhattacharya-2023-antarlekhaka</identifier>
<identifier type="doi">10.18653/v1/2023.nlposs-1.23</identifier>
<location>
<url>https://aclanthology.org/2023.nlposs-1.23/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>199</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation
%A Terdalkar, Hrishikesh
%A Bhattacharya, Arnab
%Y Tan, Liling
%Y Milajevs, Dmitrijs
%Y Chauhan, Geeticka
%Y Gwinnup, Jeremy
%Y Rippeth, Elijah
%S Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F terdalkar-bhattacharya-2023-antarlekhaka
%X One of the primary obstacles in the advancement of Natural Language Processing (NLP) technologies for low-resource languages is the lack of annotated datasets for training and testing machine learning models. In this paper, we present Antarlekhaka, a tool for manual annotation of a comprehensive set of tasks relevant to NLP. The tool is Unicode-compatible, language-agnostic, Web-deployable and supports distributed annotation by multiple simultaneous annotators. The system sports user-friendly interfaces for 8 categories of annotation tasks. These, in turn, enable the annotation of a considerably larger set of NLP tasks. The task categories include two linguistic tasks not handled by any other tool, namely, sentence boundary detection and deciding canonical word order, which are important tasks for text that is in the form of poetry. We propose the idea of sequential annotation based on small text units, where an annotator performs several tasks related to a single text unit before proceeding to the next unit. The research applications of the proposed mode of multi-task annotation are also discussed. Antarlekhaka outperforms other annotation tools in objective evaluation. It has been also used for two real-life annotation tasks on two different languages, namely, Sanskrit and Bengali. The tool is available at https://github.com/Antarlekhaka/code
%R 10.18653/v1/2023.nlposs-1.23
%U https://aclanthology.org/2023.nlposs-1.23/
%U https://doi.org/10.18653/v1/2023.nlposs-1.23
%P 199-211
Markdown (Informal)
[Antarlekhaka: A Comprehensive Tool for Multi-task Natural Language Annotation](https://aclanthology.org/2023.nlposs-1.23/) (Terdalkar & Bhattacharya, NLPOSS 2023)
ACL