@inproceedings{niraula-etal-2018-novel,
title = "A Novel Approach to Part Name Discovery in Noisy Text",
author = "Niraula, Nobal Bikram and
Whyatt, Daniel and
Kao, Anne",
editor = "Bangalore, Srinivas and
Chu-Carroll, Jennifer and
Li, Yunyao",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)",
month = jun,
year = "2018",
address = "New Orleans - Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-3021",
doi = "10.18653/v1/N18-3021",
pages = "170--176",
abstract = "As a specialized example of information extraction, part name extraction is an area that presents unique challenges. Part names are typically multi-word terms longer than two words. There is little consistency in how terms are described in noisy free text, with variations spawned by typos, ad hoc abbreviations, acronyms, and incomplete names. This makes search and analyses of parts in these data extremely challenging. In this paper, we present our algorithm, PANDA (Part Name Discovery Analytics), based on a unique method that exploits statistical, linguistic and machine learning techniques to discover part names in noisy text such as that in manufacturing quality documentation, supply chain management records, service communication logs, and maintenance reports. Experiments show that PANDA is scalable and outperforms existing techniques significantly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niraula-etal-2018-novel">
<titleInfo>
<title>A Novel Approach to Part Name Discovery in Noisy Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nobal</namePart>
<namePart type="given">Bikram</namePart>
<namePart type="family">Niraula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Whyatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Kao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srinivas</namePart>
<namePart type="family">Bangalore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Chu-Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans - Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a specialized example of information extraction, part name extraction is an area that presents unique challenges. Part names are typically multi-word terms longer than two words. There is little consistency in how terms are described in noisy free text, with variations spawned by typos, ad hoc abbreviations, acronyms, and incomplete names. This makes search and analyses of parts in these data extremely challenging. In this paper, we present our algorithm, PANDA (Part Name Discovery Analytics), based on a unique method that exploits statistical, linguistic and machine learning techniques to discover part names in noisy text such as that in manufacturing quality documentation, supply chain management records, service communication logs, and maintenance reports. Experiments show that PANDA is scalable and outperforms existing techniques significantly.</abstract>
<identifier type="citekey">niraula-etal-2018-novel</identifier>
<identifier type="doi">10.18653/v1/N18-3021</identifier>
<location>
<url>https://aclanthology.org/N18-3021</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>170</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Novel Approach to Part Name Discovery in Noisy Text
%A Niraula, Nobal Bikram
%A Whyatt, Daniel
%A Kao, Anne
%Y Bangalore, Srinivas
%Y Chu-Carroll, Jennifer
%Y Li, Yunyao
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans - Louisiana
%F niraula-etal-2018-novel
%X As a specialized example of information extraction, part name extraction is an area that presents unique challenges. Part names are typically multi-word terms longer than two words. There is little consistency in how terms are described in noisy free text, with variations spawned by typos, ad hoc abbreviations, acronyms, and incomplete names. This makes search and analyses of parts in these data extremely challenging. In this paper, we present our algorithm, PANDA (Part Name Discovery Analytics), based on a unique method that exploits statistical, linguistic and machine learning techniques to discover part names in noisy text such as that in manufacturing quality documentation, supply chain management records, service communication logs, and maintenance reports. Experiments show that PANDA is scalable and outperforms existing techniques significantly.
%R 10.18653/v1/N18-3021
%U https://aclanthology.org/N18-3021
%U https://doi.org/10.18653/v1/N18-3021
%P 170-176
Markdown (Informal)
[A Novel Approach to Part Name Discovery in Noisy Text](https://aclanthology.org/N18-3021) (Niraula et al., NAACL 2018)
ACL
- Nobal Bikram Niraula, Daniel Whyatt, and Anne Kao. 2018. A Novel Approach to Part Name Discovery in Noisy Text. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers), pages 170–176, New Orleans - Louisiana. Association for Computational Linguistics.