@inproceedings{krishnan-ragavan-2021-morphology,
title = "Morphology-Aware Meta-Embeddings for {T}amil",
author = "Krishnan, Arjun Sai and
Ragavan, Seyoon",
editor = "Durmus, Esin and
Gupta, Vivek and
Liu, Nelson and
Peng, Nanyun and
Su, Yu",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-srw.13/",
doi = "10.18653/v1/2021.naacl-srw.13",
pages = "94--111",
abstract = "In this work, we explore generating morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks. We present here the first-ever word analogy dataset for Tamil, consisting of 4499 hand-curated word tetrads across 10 semantic and 13 morphological relation types. Using a rules-based segmenter to capture morphology as well as meta-embedding techniques, we train meta-embeddings that outperform existing baselines by 16{\%} on our analogy task and appear to mitigate a previously observed trade-off between semantic and morphological accuracy."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnan-ragavan-2021-morphology">
<titleInfo>
<title>Morphology-Aware Meta-Embeddings for Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="given">Sai</namePart>
<namePart type="family">Krishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyoon</namePart>
<namePart type="family">Ragavan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we explore generating morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks. We present here the first-ever word analogy dataset for Tamil, consisting of 4499 hand-curated word tetrads across 10 semantic and 13 morphological relation types. Using a rules-based segmenter to capture morphology as well as meta-embedding techniques, we train meta-embeddings that outperform existing baselines by 16% on our analogy task and appear to mitigate a previously observed trade-off between semantic and morphological accuracy.</abstract>
<identifier type="citekey">krishnan-ragavan-2021-morphology</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-srw.13</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-srw.13/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>94</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphology-Aware Meta-Embeddings for Tamil
%A Krishnan, Arjun Sai
%A Ragavan, Seyoon
%Y Durmus, Esin
%Y Gupta, Vivek
%Y Liu, Nelson
%Y Peng, Nanyun
%Y Su, Yu
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F krishnan-ragavan-2021-morphology
%X In this work, we explore generating morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks. We present here the first-ever word analogy dataset for Tamil, consisting of 4499 hand-curated word tetrads across 10 semantic and 13 morphological relation types. Using a rules-based segmenter to capture morphology as well as meta-embedding techniques, we train meta-embeddings that outperform existing baselines by 16% on our analogy task and appear to mitigate a previously observed trade-off between semantic and morphological accuracy.
%R 10.18653/v1/2021.naacl-srw.13
%U https://aclanthology.org/2021.naacl-srw.13/
%U https://doi.org/10.18653/v1/2021.naacl-srw.13
%P 94-111
Markdown (Informal)
[Morphology-Aware Meta-Embeddings for Tamil](https://aclanthology.org/2021.naacl-srw.13/) (Krishnan & Ragavan, NAACL 2021)
ACL
- Arjun Sai Krishnan and Seyoon Ragavan. 2021. Morphology-Aware Meta-Embeddings for Tamil. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 94–111, Online. Association for Computational Linguistics.