@inproceedings{aralikatte-etal-2018-sanskrit,
title = "{S}anskrit Sandhi Splitting using seq2(seq)2",
author = "Aralikatte, Rahul and
Gantayat, Neelamadhav and
Panwar, Naveen and
Sankaran, Anush and
Mani, Senthil",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1530",
doi = "10.18653/v1/D18-1530",
pages = "4909--4914",
abstract = "In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a given compound word into its constituent morphemes. Although rules governing word splitting exists in the language, it is highly challenging to identify the location of the splits in a compound word. Though existing Sandhi splitting systems incorporate these pre-defined splitting rules, they have a low accuracy as the same compound word might be broken down in multiple ways to provide syntactically correct splits. In this research, we propose a novel deep learning architecture called Double Decoder RNN (DD-RNN), which (i) predicts the location of the split(s) with 95{\%} accuracy, and (ii) predicts the constituent words (learning the Sandhi splitting rules) with 79.5{\%} accuracy, outperforming the state-of-art by 20{\%}. Additionally, we show the generalization capability of our deep learning model, by showing competitive results in the problem of Chinese word segmentation, as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aralikatte-etal-2018-sanskrit">
<titleInfo>
<title>Sanskrit Sandhi Splitting using seq2(seq)2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Aralikatte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neelamadhav</namePart>
<namePart type="family">Gantayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naveen</namePart>
<namePart type="family">Panwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anush</namePart>
<namePart type="family">Sankaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senthil</namePart>
<namePart type="family">Mani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a given compound word into its constituent morphemes. Although rules governing word splitting exists in the language, it is highly challenging to identify the location of the splits in a compound word. Though existing Sandhi splitting systems incorporate these pre-defined splitting rules, they have a low accuracy as the same compound word might be broken down in multiple ways to provide syntactically correct splits. In this research, we propose a novel deep learning architecture called Double Decoder RNN (DD-RNN), which (i) predicts the location of the split(s) with 95% accuracy, and (ii) predicts the constituent words (learning the Sandhi splitting rules) with 79.5% accuracy, outperforming the state-of-art by 20%. Additionally, we show the generalization capability of our deep learning model, by showing competitive results in the problem of Chinese word segmentation, as well.</abstract>
<identifier type="citekey">aralikatte-etal-2018-sanskrit</identifier>
<identifier type="doi">10.18653/v1/D18-1530</identifier>
<location>
<url>https://aclanthology.org/D18-1530</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4909</start>
<end>4914</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sanskrit Sandhi Splitting using seq2(seq)2
%A Aralikatte, Rahul
%A Gantayat, Neelamadhav
%A Panwar, Naveen
%A Sankaran, Anush
%A Mani, Senthil
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F aralikatte-etal-2018-sanskrit
%X In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a given compound word into its constituent morphemes. Although rules governing word splitting exists in the language, it is highly challenging to identify the location of the splits in a compound word. Though existing Sandhi splitting systems incorporate these pre-defined splitting rules, they have a low accuracy as the same compound word might be broken down in multiple ways to provide syntactically correct splits. In this research, we propose a novel deep learning architecture called Double Decoder RNN (DD-RNN), which (i) predicts the location of the split(s) with 95% accuracy, and (ii) predicts the constituent words (learning the Sandhi splitting rules) with 79.5% accuracy, outperforming the state-of-art by 20%. Additionally, we show the generalization capability of our deep learning model, by showing competitive results in the problem of Chinese word segmentation, as well.
%R 10.18653/v1/D18-1530
%U https://aclanthology.org/D18-1530
%U https://doi.org/10.18653/v1/D18-1530
%P 4909-4914
Markdown (Informal)
[Sanskrit Sandhi Splitting using seq2(seq)2](https://aclanthology.org/D18-1530) (Aralikatte et al., EMNLP 2018)
ACL
- Rahul Aralikatte, Neelamadhav Gantayat, Naveen Panwar, Anush Sankaran, and Senthil Mani. 2018. Sanskrit Sandhi Splitting using seq2(seq)2. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4909–4914, Brussels, Belgium. Association for Computational Linguistics.