@inproceedings{sandhan-etal-2023-depnecti,
title = "{D}ep{N}e{CTI}: Dependency-based Nested Compound Type Identification for {S}anskrit",
author = "Sandhan, Jivnesh and
Narsupalli, Yaswanth and
Muppirala, Sreevatsa and
Krishnan, Sriram and
Satuluri, Pavankumar and
Kulkarni, Amba and
Goyal, Pawan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.914",
doi = "10.18653/v1/2023.findings-emnlp.914",
pages = "13679--13692",
abstract = "Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound{'}s components is crucial for deciphering its meaning. Earlier approaches in Sanskrit have focused on binary compounds and neglected the multi-component compound setting. This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them. To the best of our knowledge, this is the first attempt in the field of lexical semantics to propose this task. We present 2 newly annotated datasets including an out-of-domain dataset for this task. We also benchmark these datasets by exploring the efficacy of the standard problem formulations such as nested named entity recognition, constituency parsing and seq2seq, etc. We present a novel framework named DepNeCTI: Dependency-based Nested Compound Type Identifier that surpasses the performance of the best baseline with an average absolute improvement of 13.1 points F1-score in terms of Labeled Span Score (LSS) and a 5-fold enhancement in inference efficiency. In line with the previous findings in the binary Sanskrit compound identification task, context provides benefits for the NeCTI task. The codebase and datasets are publicly available at: https://github.com/yaswanth-iitkgp/DepNeCTI",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sandhan-etal-2023-depnecti">
<titleInfo>
<title>DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jivnesh</namePart>
<namePart type="family">Sandhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaswanth</namePart>
<namePart type="family">Narsupalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreevatsa</namePart>
<namePart type="family">Muppirala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriram</namePart>
<namePart type="family">Krishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavankumar</namePart>
<namePart type="family">Satuluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amba</namePart>
<namePart type="family">Kulkarni</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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound’s components is crucial for deciphering its meaning. Earlier approaches in Sanskrit have focused on binary compounds and neglected the multi-component compound setting. This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them. To the best of our knowledge, this is the first attempt in the field of lexical semantics to propose this task. We present 2 newly annotated datasets including an out-of-domain dataset for this task. We also benchmark these datasets by exploring the efficacy of the standard problem formulations such as nested named entity recognition, constituency parsing and seq2seq, etc. We present a novel framework named DepNeCTI: Dependency-based Nested Compound Type Identifier that surpasses the performance of the best baseline with an average absolute improvement of 13.1 points F1-score in terms of Labeled Span Score (LSS) and a 5-fold enhancement in inference efficiency. In line with the previous findings in the binary Sanskrit compound identification task, context provides benefits for the NeCTI task. The codebase and datasets are publicly available at: https://github.com/yaswanth-iitkgp/DepNeCTI</abstract>
<identifier type="citekey">sandhan-etal-2023-depnecti</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.914</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.914</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13679</start>
<end>13692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit
%A Sandhan, Jivnesh
%A Narsupalli, Yaswanth
%A Muppirala, Sreevatsa
%A Krishnan, Sriram
%A Satuluri, Pavankumar
%A Kulkarni, Amba
%A Goyal, Pawan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sandhan-etal-2023-depnecti
%X Multi-component compounding is a prevalent phenomenon in Sanskrit, and understanding the implicit structure of a compound’s components is crucial for deciphering its meaning. Earlier approaches in Sanskrit have focused on binary compounds and neglected the multi-component compound setting. This work introduces the novel task of nested compound type identification (NeCTI), which aims to identify nested spans of a multi-component compound and decode the implicit semantic relations between them. To the best of our knowledge, this is the first attempt in the field of lexical semantics to propose this task. We present 2 newly annotated datasets including an out-of-domain dataset for this task. We also benchmark these datasets by exploring the efficacy of the standard problem formulations such as nested named entity recognition, constituency parsing and seq2seq, etc. We present a novel framework named DepNeCTI: Dependency-based Nested Compound Type Identifier that surpasses the performance of the best baseline with an average absolute improvement of 13.1 points F1-score in terms of Labeled Span Score (LSS) and a 5-fold enhancement in inference efficiency. In line with the previous findings in the binary Sanskrit compound identification task, context provides benefits for the NeCTI task. The codebase and datasets are publicly available at: https://github.com/yaswanth-iitkgp/DepNeCTI
%R 10.18653/v1/2023.findings-emnlp.914
%U https://aclanthology.org/2023.findings-emnlp.914
%U https://doi.org/10.18653/v1/2023.findings-emnlp.914
%P 13679-13692
Markdown (Informal)
[DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit](https://aclanthology.org/2023.findings-emnlp.914) (Sandhan et al., Findings 2023)
ACL