Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context

Gabriele Pergola; Yulan He; David Lowe

Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context

Gabriele Pergola, Yulan He, David Lowe

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Making sense of words often requires to simultaneously
examine the surrounding context of a term as well as the
global themes characterizing the overall corpus. Several
topic models have already exploited word embeddings
to recognize local context, however, it has been weakly
combined with the global context during the topic inference.
This paper proposes to extract topical phrases
corroborating the word embedding information with the
global context detected by Latent Semantic Analysis,
and then combine them by means of the Polya urn ´
model. To highlight the effectiveness of this combined
approach the model was assessed analyzing clinical reports,
a challenging scenario characterized by technical
jargon and a limited word statistics available. Results
show it outperforms the state-of-the-art approaches in
terms of both topic coherence and computational cost.

Original language	English
Title of host publication	The 2nd AAAI Workshop on Health Intelligence
Pages	499-506
Number of pages	8
Publication status	E-pub ahead of print - 20 Jun 2018
Event	2018 Workshop on Health Intelligence (W3PHIAI 2018) - New Orleans, United States Duration: 2 Feb 2018 → 3 Feb 2018

Conference

Conference	2018 Workshop on Health Intelligence (W3PHIAI 2018)
Country/Territory	United States
City	New Orleans
Period	2/02/18 → 3/02/18

Bibliographical note

Copyright
© 2018, Association for the Advancement of Artificial
Intelligence (www.aaai.org). All rights reserved.

Access to Document

Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context
Copyright ©2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Accepted author manuscript, 740 KBLicence: Unspecified

Cite this

@inproceedings{85b6d73bd5e047eb865862bac64b4f6c,

title = "Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context",

abstract = "Making sense of words often requires to simultaneouslyexamine the surrounding context of a term as well as theglobal themes characterizing the overall corpus. Severaltopic models have already exploited word embeddingsto recognize local context, however, it has been weaklycombined with the global context during the topic inference.This paper proposes to extract topical phrasescorroborating the word embedding information with theglobal context detected by Latent Semantic Analysis,and then combine them by means of the Polya urn ´model. To highlight the effectiveness of this combinedapproach the model was assessed analyzing clinical reports,a challenging scenario characterized by technicaljargon and a limited word statistics available. Resultsshow it outperforms the state-of-the-art approaches interms of both topic coherence and computational cost.",

author = "Gabriele Pergola and Yulan He and David Lowe",

note = "Copyright {\textcopyright} 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. ; 2018 Workshop on Health Intelligence (W3PHIAI 2018) ; Conference date: 02-02-2018 Through 03-02-2018",

year = "2018",

month = jun,

day = "20",

language = "English",

pages = "499--506",

booktitle = "The 2nd AAAI Workshop on Health Intelligence",

}

TY - GEN

T1 - Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context

AU - Pergola, Gabriele

AU - He, Yulan

AU - Lowe, David

PY - 2018/6/20

Y1 - 2018/6/20

N2 - Making sense of words often requires to simultaneouslyexamine the surrounding context of a term as well as theglobal themes characterizing the overall corpus. Severaltopic models have already exploited word embeddingsto recognize local context, however, it has been weaklycombined with the global context during the topic inference.This paper proposes to extract topical phrasescorroborating the word embedding information with theglobal context detected by Latent Semantic Analysis,and then combine them by means of the Polya urn ´model. To highlight the effectiveness of this combinedapproach the model was assessed analyzing clinical reports,a challenging scenario characterized by technicaljargon and a limited word statistics available. Resultsshow it outperforms the state-of-the-art approaches interms of both topic coherence and computational cost.

AB - Making sense of words often requires to simultaneouslyexamine the surrounding context of a term as well as theglobal themes characterizing the overall corpus. Severaltopic models have already exploited word embeddingsto recognize local context, however, it has been weaklycombined with the global context during the topic inference.This paper proposes to extract topical phrasescorroborating the word embedding information with theglobal context detected by Latent Semantic Analysis,and then combine them by means of the Polya urn ´model. To highlight the effectiveness of this combinedapproach the model was assessed analyzing clinical reports,a challenging scenario characterized by technicaljargon and a limited word statistics available. Resultsshow it outperforms the state-of-the-art approaches interms of both topic coherence and computational cost.

UR - https://aaai.org/ocs/index.php/WS/AAAIW18/paper/view/16612

M3 - Conference publication

SP - 499

EP - 506

BT - The 2nd AAAI Workshop on Health Intelligence

T2 - 2018 Workshop on Health Intelligence (W3PHIAI 2018)

Y2 - 2 February 2018 through 3 February 2018

ER -

Topical Phrase Extraction from Clinical Reports by Incorporating both Local and Global Context

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this