@inproceedings{das-etal-2018-phrase2vecglm,
title = "{P}hrase2{V}ec{GLM}: Neural generalized language model{--}based semantic tagging for complex query reformulation in medical {IR}",
author = "Das, Manirupa and
Fosler-Lussier, Eric and
Lin, Simon and
Moosavinasab, Soheil and
Chen, David and
Rust, Steve and
Huang, Yungui and
Ramnath, Rajiv",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the {B}io{NLP} 2018 workshop",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2313/",
doi = "10.18653/v1/W18-2313",
pages = "118--128",
abstract = "In this work, we develop a novel, completely unsupervised, neural language model-based document ranking approach to semantic tagging of documents, using the document to be tagged as a query into the GLM to retrieve candidate phrases from top-ranked related documents, thus associating every document with novel related concepts extracted from the text. For this we extend the word embedding-based general language model due to Ganguly et al 2015, to employ phrasal embeddings, and use the semantic tags thus obtained for downstream query expansion, both directly and in feedback loop settings. Our method, evaluated using the TREC 2016 clinical decision support challenge dataset, shows statistically significant improvement not only over various baselines that use standard MeSH terms and UMLS concepts for query expansion, but also over baselines using human expert{--}assigned concept tags for the queries, run on top of a standard Okapi BM25{--}based document retrieval system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2018-phrase2vecglm">
<titleInfo>
<title>Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manirupa</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Fosler-Lussier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soheil</namePart>
<namePart type="family">Moosavinasab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Rust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yungui</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="family">Ramnath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the BioNLP 2018 workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</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">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we develop a novel, completely unsupervised, neural language model-based document ranking approach to semantic tagging of documents, using the document to be tagged as a query into the GLM to retrieve candidate phrases from top-ranked related documents, thus associating every document with novel related concepts extracted from the text. For this we extend the word embedding-based general language model due to Ganguly et al 2015, to employ phrasal embeddings, and use the semantic tags thus obtained for downstream query expansion, both directly and in feedback loop settings. Our method, evaluated using the TREC 2016 clinical decision support challenge dataset, shows statistically significant improvement not only over various baselines that use standard MeSH terms and UMLS concepts for query expansion, but also over baselines using human expert–assigned concept tags for the queries, run on top of a standard Okapi BM25–based document retrieval system.</abstract>
<identifier type="citekey">das-etal-2018-phrase2vecglm</identifier>
<identifier type="doi">10.18653/v1/W18-2313</identifier>
<location>
<url>https://aclanthology.org/W18-2313/</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>118</start>
<end>128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR
%A Das, Manirupa
%A Fosler-Lussier, Eric
%A Lin, Simon
%A Moosavinasab, Soheil
%A Chen, David
%A Rust, Steve
%A Huang, Yungui
%A Ramnath, Rajiv
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the BioNLP 2018 workshop
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F das-etal-2018-phrase2vecglm
%X In this work, we develop a novel, completely unsupervised, neural language model-based document ranking approach to semantic tagging of documents, using the document to be tagged as a query into the GLM to retrieve candidate phrases from top-ranked related documents, thus associating every document with novel related concepts extracted from the text. For this we extend the word embedding-based general language model due to Ganguly et al 2015, to employ phrasal embeddings, and use the semantic tags thus obtained for downstream query expansion, both directly and in feedback loop settings. Our method, evaluated using the TREC 2016 clinical decision support challenge dataset, shows statistically significant improvement not only over various baselines that use standard MeSH terms and UMLS concepts for query expansion, but also over baselines using human expert–assigned concept tags for the queries, run on top of a standard Okapi BM25–based document retrieval system.
%R 10.18653/v1/W18-2313
%U https://aclanthology.org/W18-2313/
%U https://doi.org/10.18653/v1/W18-2313
%P 118-128
Markdown (Informal)
[Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR](https://aclanthology.org/W18-2313/) (Das et al., BioNLP 2018)
ACL
- Manirupa Das, Eric Fosler-Lussier, Simon Lin, Soheil Moosavinasab, David Chen, Steve Rust, Yungui Huang, and Rajiv Ramnath. 2018. Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR. In Proceedings of the BioNLP 2018 workshop, pages 118–128, Melbourne, Australia. Association for Computational Linguistics.