@inproceedings{krishna-etal-2019-poetry,
title = "Poetry to Prose Conversion in {S}anskrit as a Linearisation Task: A Case for Low-Resource Languages",
author = "Krishna, Amrith and
Sharma, Vishnu and
Santra, Bishal and
Chakraborty, Aishik and
Satuluri, Pavankumar and
Goyal, Pawan",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1111",
doi = "10.18653/v1/P19-1111",
pages = "1160--1166",
abstract = "The word ordering in a Sanskrit verse is often not aligned with its corresponding prose order. Conversion of the verse to its corresponding prose helps in better comprehension of the construction. Owing to the resource constraints, we formulate this task as a word ordering (linearisation) task. In doing so, we completely ignore the word arrangement at the verse side. k{\=a}vya guru, the approach we propose, essentially consists of a pipeline of two pretraining steps followed by a seq2seq model. The first pretraining step learns task-specific token embeddings from pretrained embeddings. In the next step, we generate multiple possible hypotheses for possible word arrangements of the input {\%}using another pretraining step. We then use them as inputs to a neural seq2seq model for the final prediction. We empirically show that the hypotheses generated by our pretraining step result in predictions that consistently outperform predictions based on the original order in the verse. Overall, k{\=a}vya guru outperforms current state of the art models in linearisation for the poetry to prose conversion task in Sanskrit.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishna-etal-2019-poetry">
<titleInfo>
<title>Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amrith</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bishal</namePart>
<namePart type="family">Santra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishik</namePart>
<namePart type="family">Chakraborty</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">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The word ordering in a Sanskrit verse is often not aligned with its corresponding prose order. Conversion of the verse to its corresponding prose helps in better comprehension of the construction. Owing to the resource constraints, we formulate this task as a word ordering (linearisation) task. In doing so, we completely ignore the word arrangement at the verse side. kāvya guru, the approach we propose, essentially consists of a pipeline of two pretraining steps followed by a seq2seq model. The first pretraining step learns task-specific token embeddings from pretrained embeddings. In the next step, we generate multiple possible hypotheses for possible word arrangements of the input %using another pretraining step. We then use them as inputs to a neural seq2seq model for the final prediction. We empirically show that the hypotheses generated by our pretraining step result in predictions that consistently outperform predictions based on the original order in the verse. Overall, kāvya guru outperforms current state of the art models in linearisation for the poetry to prose conversion task in Sanskrit.</abstract>
<identifier type="citekey">krishna-etal-2019-poetry</identifier>
<identifier type="doi">10.18653/v1/P19-1111</identifier>
<location>
<url>https://aclanthology.org/P19-1111</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>1160</start>
<end>1166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages
%A Krishna, Amrith
%A Sharma, Vishnu
%A Santra, Bishal
%A Chakraborty, Aishik
%A Satuluri, Pavankumar
%A Goyal, Pawan
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F krishna-etal-2019-poetry
%X The word ordering in a Sanskrit verse is often not aligned with its corresponding prose order. Conversion of the verse to its corresponding prose helps in better comprehension of the construction. Owing to the resource constraints, we formulate this task as a word ordering (linearisation) task. In doing so, we completely ignore the word arrangement at the verse side. kāvya guru, the approach we propose, essentially consists of a pipeline of two pretraining steps followed by a seq2seq model. The first pretraining step learns task-specific token embeddings from pretrained embeddings. In the next step, we generate multiple possible hypotheses for possible word arrangements of the input %using another pretraining step. We then use them as inputs to a neural seq2seq model for the final prediction. We empirically show that the hypotheses generated by our pretraining step result in predictions that consistently outperform predictions based on the original order in the verse. Overall, kāvya guru outperforms current state of the art models in linearisation for the poetry to prose conversion task in Sanskrit.
%R 10.18653/v1/P19-1111
%U https://aclanthology.org/P19-1111
%U https://doi.org/10.18653/v1/P19-1111
%P 1160-1166
Markdown (Informal)
[Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages](https://aclanthology.org/P19-1111) (Krishna et al., ACL 2019)
ACL