@inproceedings{krishna-etal-2018-free,
title = "Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in {S}anskrit",
author = "Krishna, Amrith and
Santra, Bishal and
Bandaru, Sasi Prasanth and
Sahu, Gaurav and
Sharma, Vishnu Dutt and
Satuluri, Pavankumar and
Goyal, Pawan",
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/D18-1276",
doi = "10.18653/v1/D18-1276",
pages = "2550--2561",
abstract = "The configurational information in sentences of a free word order language such as Sanskrit is of limited use. Thus, the context of the entire sentence will be desirable even for basic processing tasks such as word segmentation. We propose a structured prediction framework that jointly solves the word segmentation and morphological tagging tasks in Sanskrit. We build an energy based model where we adopt approaches generally employed in graph based parsing techniques (McDonald et al., 2005a; Carreras, 2007). Our model outperforms the state of the art with an F-Score of 96.92 (percentage improvement of 7.06{\%}) while using less than one tenth of the task-specific training data. We find that the use of a graph based approach instead of a traditional lattice-based sequential labelling approach leads to a percentage gain of 12.6{\%} in F-Score for the segmentation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishna-etal-2018-free">
<titleInfo>
<title>Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit</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">Bishal</namePart>
<namePart type="family">Santra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sasi</namePart>
<namePart type="given">Prasanth</namePart>
<namePart type="family">Bandaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Sahu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="given">Dutt</namePart>
<namePart type="family">Sharma</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>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>The configurational information in sentences of a free word order language such as Sanskrit is of limited use. Thus, the context of the entire sentence will be desirable even for basic processing tasks such as word segmentation. We propose a structured prediction framework that jointly solves the word segmentation and morphological tagging tasks in Sanskrit. We build an energy based model where we adopt approaches generally employed in graph based parsing techniques (McDonald et al., 2005a; Carreras, 2007). Our model outperforms the state of the art with an F-Score of 96.92 (percentage improvement of 7.06%) while using less than one tenth of the task-specific training data. We find that the use of a graph based approach instead of a traditional lattice-based sequential labelling approach leads to a percentage gain of 12.6% in F-Score for the segmentation task.</abstract>
<identifier type="citekey">krishna-etal-2018-free</identifier>
<identifier type="doi">10.18653/v1/D18-1276</identifier>
<location>
<url>https://aclanthology.org/D18-1276</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2550</start>
<end>2561</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit
%A Krishna, Amrith
%A Santra, Bishal
%A Bandaru, Sasi Prasanth
%A Sahu, Gaurav
%A Sharma, Vishnu Dutt
%A Satuluri, Pavankumar
%A Goyal, Pawan
%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 krishna-etal-2018-free
%X The configurational information in sentences of a free word order language such as Sanskrit is of limited use. Thus, the context of the entire sentence will be desirable even for basic processing tasks such as word segmentation. We propose a structured prediction framework that jointly solves the word segmentation and morphological tagging tasks in Sanskrit. We build an energy based model where we adopt approaches generally employed in graph based parsing techniques (McDonald et al., 2005a; Carreras, 2007). Our model outperforms the state of the art with an F-Score of 96.92 (percentage improvement of 7.06%) while using less than one tenth of the task-specific training data. We find that the use of a graph based approach instead of a traditional lattice-based sequential labelling approach leads to a percentage gain of 12.6% in F-Score for the segmentation task.
%R 10.18653/v1/D18-1276
%U https://aclanthology.org/D18-1276
%U https://doi.org/10.18653/v1/D18-1276
%P 2550-2561
Markdown (Informal)
[Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit](https://aclanthology.org/D18-1276) (Krishna et al., EMNLP 2018)
ACL