NegAIT: A new parser for medical text simplification using morphological, sentential and double negation

Partha Mukherjee, Gondy Augusta Leroy, David Kauchak, Srinidhi Rajanarayanan, Damian Y. Romero Diaz, Nicole P Yuan, T. Gail Pritchard, Sonia - Colina

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Many different text features influence text readability and content comprehension. Negation is commonly suggested as one such feature, but few general-purpose tools exist to discover negation and studies of the impact of negation on text readability are rare. In this paper, we introduce a new negation parser (NegAIT) for detecting morphological, sentential, and double negation. We evaluated the parser using a human annotated gold standard containing 500 Wikipedia sentences and achieved 95%, 89% and 67% precision with 100%, 80%, and 67% recall, respectively. We also investigate two applications of this new negation parser. First, we performed a corpus statistics study to demonstrate different negation usage in easy and difficult text. Negation usage was compared in six corpora: patient blogs (4 K sentences), Cochrane reviews (91 K sentences), PubMed abstracts (20 K sentences), clinical trial texts (48 K sentences), and English and Simple English Wikipedia articles for different medical topics (60 K and 6 K sentences). The most difficult text contained the least negation. However, when comparing negation types, difficult texts (i.e., Cochrane, PubMed, English Wikipedia and clinical trials) contained significantly (p < 0.01) more morphological negations. Second, we conducted a predictive analytics study to show the importance of negation in distinguishing between easy and difficulty text. Five binary classifiers (Naïve Bayes, SVM, decision tree, logistic regression and linear regression) were trained using only negation information. All classifiers achieved better performance than the majority baseline. The Naïve Bayes’ classifier achieved the highest accuracy at 77% (9% higher than the majority baseline).

Original languageEnglish (US)
Pages (from-to)55-62
Number of pages8
JournalJournal of Biomedical Informatics
Volume69
DOIs
StatePublished - May 1 2017

Fingerprint

Classifiers
PubMed
Blogging
Clinical Trials
Decision Trees
Blogs
Decision trees
Linear regression
Logistics
Linear Models
Logistic Models
Statistics
Predictive analytics

Keywords

  • Health literacy
  • Negation
  • NLP
  • Readability
  • Text simplification

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

NegAIT : A new parser for medical text simplification using morphological, sentential and double negation. / Mukherjee, Partha; Leroy, Gondy Augusta; Kauchak, David; Rajanarayanan, Srinidhi; Romero Diaz, Damian Y.; Yuan, Nicole P; Pritchard, T. Gail; Colina, Sonia -.

In: Journal of Biomedical Informatics, Vol. 69, 01.05.2017, p. 55-62.

Research output: Contribution to journalArticle

Mukherjee, Partha ; Leroy, Gondy Augusta ; Kauchak, David ; Rajanarayanan, Srinidhi ; Romero Diaz, Damian Y. ; Yuan, Nicole P ; Pritchard, T. Gail ; Colina, Sonia -. / NegAIT : A new parser for medical text simplification using morphological, sentential and double negation. In: Journal of Biomedical Informatics. 2017 ; Vol. 69. pp. 55-62.
@article{fb4ec16d05994daaac24682ac026f14d,
title = "NegAIT: A new parser for medical text simplification using morphological, sentential and double negation",
abstract = "Many different text features influence text readability and content comprehension. Negation is commonly suggested as one such feature, but few general-purpose tools exist to discover negation and studies of the impact of negation on text readability are rare. In this paper, we introduce a new negation parser (NegAIT) for detecting morphological, sentential, and double negation. We evaluated the parser using a human annotated gold standard containing 500 Wikipedia sentences and achieved 95{\%}, 89{\%} and 67{\%} precision with 100{\%}, 80{\%}, and 67{\%} recall, respectively. We also investigate two applications of this new negation parser. First, we performed a corpus statistics study to demonstrate different negation usage in easy and difficult text. Negation usage was compared in six corpora: patient blogs (4 K sentences), Cochrane reviews (91 K sentences), PubMed abstracts (20 K sentences), clinical trial texts (48 K sentences), and English and Simple English Wikipedia articles for different medical topics (60 K and 6 K sentences). The most difficult text contained the least negation. However, when comparing negation types, difficult texts (i.e., Cochrane, PubMed, English Wikipedia and clinical trials) contained significantly (p < 0.01) more morphological negations. Second, we conducted a predictive analytics study to show the importance of negation in distinguishing between easy and difficulty text. Five binary classifiers (Na{\"i}ve Bayes, SVM, decision tree, logistic regression and linear regression) were trained using only negation information. All classifiers achieved better performance than the majority baseline. The Na{\"i}ve Bayes’ classifier achieved the highest accuracy at 77{\%} (9{\%} higher than the majority baseline).",
keywords = "Health literacy, Negation, NLP, Readability, Text simplification",
author = "Partha Mukherjee and Leroy, {Gondy Augusta} and David Kauchak and Srinidhi Rajanarayanan and {Romero Diaz}, {Damian Y.} and Yuan, {Nicole P} and Pritchard, {T. Gail} and Colina, {Sonia -}",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.jbi.2017.03.014",
language = "English (US)",
volume = "69",
pages = "55--62",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - NegAIT

T2 - A new parser for medical text simplification using morphological, sentential and double negation

AU - Mukherjee, Partha

AU - Leroy, Gondy Augusta

AU - Kauchak, David

AU - Rajanarayanan, Srinidhi

AU - Romero Diaz, Damian Y.

AU - Yuan, Nicole P

AU - Pritchard, T. Gail

AU - Colina, Sonia -

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Many different text features influence text readability and content comprehension. Negation is commonly suggested as one such feature, but few general-purpose tools exist to discover negation and studies of the impact of negation on text readability are rare. In this paper, we introduce a new negation parser (NegAIT) for detecting morphological, sentential, and double negation. We evaluated the parser using a human annotated gold standard containing 500 Wikipedia sentences and achieved 95%, 89% and 67% precision with 100%, 80%, and 67% recall, respectively. We also investigate two applications of this new negation parser. First, we performed a corpus statistics study to demonstrate different negation usage in easy and difficult text. Negation usage was compared in six corpora: patient blogs (4 K sentences), Cochrane reviews (91 K sentences), PubMed abstracts (20 K sentences), clinical trial texts (48 K sentences), and English and Simple English Wikipedia articles for different medical topics (60 K and 6 K sentences). The most difficult text contained the least negation. However, when comparing negation types, difficult texts (i.e., Cochrane, PubMed, English Wikipedia and clinical trials) contained significantly (p < 0.01) more morphological negations. Second, we conducted a predictive analytics study to show the importance of negation in distinguishing between easy and difficulty text. Five binary classifiers (Naïve Bayes, SVM, decision tree, logistic regression and linear regression) were trained using only negation information. All classifiers achieved better performance than the majority baseline. The Naïve Bayes’ classifier achieved the highest accuracy at 77% (9% higher than the majority baseline).

AB - Many different text features influence text readability and content comprehension. Negation is commonly suggested as one such feature, but few general-purpose tools exist to discover negation and studies of the impact of negation on text readability are rare. In this paper, we introduce a new negation parser (NegAIT) for detecting morphological, sentential, and double negation. We evaluated the parser using a human annotated gold standard containing 500 Wikipedia sentences and achieved 95%, 89% and 67% precision with 100%, 80%, and 67% recall, respectively. We also investigate two applications of this new negation parser. First, we performed a corpus statistics study to demonstrate different negation usage in easy and difficult text. Negation usage was compared in six corpora: patient blogs (4 K sentences), Cochrane reviews (91 K sentences), PubMed abstracts (20 K sentences), clinical trial texts (48 K sentences), and English and Simple English Wikipedia articles for different medical topics (60 K and 6 K sentences). The most difficult text contained the least negation. However, when comparing negation types, difficult texts (i.e., Cochrane, PubMed, English Wikipedia and clinical trials) contained significantly (p < 0.01) more morphological negations. Second, we conducted a predictive analytics study to show the importance of negation in distinguishing between easy and difficulty text. Five binary classifiers (Naïve Bayes, SVM, decision tree, logistic regression and linear regression) were trained using only negation information. All classifiers achieved better performance than the majority baseline. The Naïve Bayes’ classifier achieved the highest accuracy at 77% (9% higher than the majority baseline).

KW - Health literacy

KW - Negation

KW - NLP

KW - Readability

KW - Text simplification

UR - http://www.scopus.com/inward/record.url?scp=85016487612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016487612&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2017.03.014

DO - 10.1016/j.jbi.2017.03.014

M3 - Article

C2 - 28342946

AN - SCOPUS:85016487612

VL - 69

SP - 55

EP - 62

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

ER -