@inproceedings{rajput-etal-2020-n,
title = "N-Grams {T}ext{R}ank A Novel Domain Keyword Extraction Technique",
author = "Rajput, Saransh and
Gahoi, Akshat and
Reddy, Manvith and
Mishra Sharma, Dipti",
editor = "Sharma, Dipti Misra and
Ekbal, Asif and
Arora, Karunesh and
Naskar, Sudip Kumar and
Ganguly, Dipankar and
L, Sobha and
Mamidi, Radhika and
Arora, Sunita and
Mishra, Pruthwik and
Mujadia, Vandan",
booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON): TermTraction 2020 Shared Task",
month = dec,
year = "2020",
address = "Patna, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2020.icon-termtraction.3",
pages = "9--12",
abstract = "The rapid growth of the internet has given us a wealth of information and data spread across the web. However, as the data begins to grow we simultaneously face the grave problem of an \textit{Information Explosion}. An abundance of data can lead to large scale data management problems as well as the loss of the true meaning of the data. In this paper, we present an advanced domain specific keyword extraction algorithm in order to tackle this problem of paramount importance. Our algorithm is based on a modified version of TextRank algorithm - an algorithm based on PageRank to successfully determine the keywords from a domain specific document. Furthermore, this paper proposes a modification to the traditional TextRank algorithm that takes into account bigrams and trigrams and returns results with an extremely high precision. We observe how the precision and f1-score of this model outperforms other models in many domains and the recall can be easily increased by increasing the number of results without affecting the precision. We also discuss about the future work of extending the same algorithm to Indian languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajput-etal-2020-n">
<titleInfo>
<title>N-Grams TextRank A Novel Domain Keyword Extraction Technique</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saransh</namePart>
<namePart type="family">Rajput</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshat</namePart>
<namePart type="family">Gahoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manvith</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Mishra Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Natural Language Processing (ICON): TermTraction 2020 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karunesh</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="family">L</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunita</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Patna, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid growth of the internet has given us a wealth of information and data spread across the web. However, as the data begins to grow we simultaneously face the grave problem of an Information Explosion. An abundance of data can lead to large scale data management problems as well as the loss of the true meaning of the data. In this paper, we present an advanced domain specific keyword extraction algorithm in order to tackle this problem of paramount importance. Our algorithm is based on a modified version of TextRank algorithm - an algorithm based on PageRank to successfully determine the keywords from a domain specific document. Furthermore, this paper proposes a modification to the traditional TextRank algorithm that takes into account bigrams and trigrams and returns results with an extremely high precision. We observe how the precision and f1-score of this model outperforms other models in many domains and the recall can be easily increased by increasing the number of results without affecting the precision. We also discuss about the future work of extending the same algorithm to Indian languages.</abstract>
<identifier type="citekey">rajput-etal-2020-n</identifier>
<location>
<url>https://aclanthology.org/2020.icon-termtraction.3</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>9</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N-Grams TextRank A Novel Domain Keyword Extraction Technique
%A Rajput, Saransh
%A Gahoi, Akshat
%A Reddy, Manvith
%A Mishra Sharma, Dipti
%Y Sharma, Dipti Misra
%Y Ekbal, Asif
%Y Arora, Karunesh
%Y Naskar, Sudip Kumar
%Y Ganguly, Dipankar
%Y L, Sobha
%Y Mamidi, Radhika
%Y Arora, Sunita
%Y Mishra, Pruthwik
%Y Mujadia, Vandan
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON): TermTraction 2020 Shared Task
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Patna, India
%F rajput-etal-2020-n
%X The rapid growth of the internet has given us a wealth of information and data spread across the web. However, as the data begins to grow we simultaneously face the grave problem of an Information Explosion. An abundance of data can lead to large scale data management problems as well as the loss of the true meaning of the data. In this paper, we present an advanced domain specific keyword extraction algorithm in order to tackle this problem of paramount importance. Our algorithm is based on a modified version of TextRank algorithm - an algorithm based on PageRank to successfully determine the keywords from a domain specific document. Furthermore, this paper proposes a modification to the traditional TextRank algorithm that takes into account bigrams and trigrams and returns results with an extremely high precision. We observe how the precision and f1-score of this model outperforms other models in many domains and the recall can be easily increased by increasing the number of results without affecting the precision. We also discuss about the future work of extending the same algorithm to Indian languages.
%U https://aclanthology.org/2020.icon-termtraction.3
%P 9-12
Markdown (Informal)
[N-Grams TextRank A Novel Domain Keyword Extraction Technique](https://aclanthology.org/2020.icon-termtraction.3) (Rajput et al., ICON 2020)
ACL
- Saransh Rajput, Akshat Gahoi, Manvith Reddy, and Dipti Mishra Sharma. 2020. N-Grams TextRank A Novel Domain Keyword Extraction Technique. In Proceedings of the 17th International Conference on Natural Language Processing (ICON): TermTraction 2020 Shared Task, pages 9–12, Patna, India. NLP Association of India (NLPAI).