Keyphrase Extraction for Technical Language Processing

Thumbnail Image

Files

jres.126.053.pdf (1.17 MB)

Links to Files

https://nvlpubs.nist.gov/nistpubs/jres/126/jres.126.053.pdf

Permanent Link

https://doi.org/10.6028/jres.126.053
 http://hdl.handle.net/11603/24456

Collections

UMBC Information Systems Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-4698-6034

Date

2021-03-09

Type of Work

journal articles
Text

Department

Program

Citation of Original Publication

Dima A, Massey A (2021) Keyphrase Extraction for Technical Language Processing. J Res Natl Inst Stan 126:126053. https://doi.org/10.6028/jres.126.053.

Rights

This is a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
Public Domain Mark 1.0

Subjects

Abstract

Keyphrase extraction is an important facet of annotation tools that offer the provision of the metadata necessary for technical language processing (TLP). Because TLP imposes additional requirements on typical natural language processing (NLP) methods, we examined TLP keyphrase extraction through the lens of a hypothetical toolkit which consists of a combination of text features and classifers suitable for use in low-resource TLP applications. We compared two approaches for keyphrase extraction: The frst which applied our toolkit-based methods that used only distributional features of words and phrases, and the second was the Maui automatic topic indexer, a well-known academic method. Performance was measured against two collections of technical literature: 1153 articles from Journal of Chemical Thermodynamics (JCT) curated by the National Institute of Standards and Technology Thermodynamics Research Center (TRC) and 244 articles from Task 5 of the Workshop on Semantic Evaluation (SemEval). Both collections have author-provided keyphrases available; the SemEval articles also have reader-provided keyphrases. Our fndings indicate that our toolkit approach was competitive with Maui when author-provided keyphrases were frst removed from the text. For the TRC-JCT articles, the Maui automatic topic indexer reported an F-measure of 29.4 % while our toolkit approach obtained an F-measure of 28.2 %. For the SemEval articles, our toolkit approach using a Naïve Bayes classifer resulted in an F-measure of 20.8 %, which outperformed Maui’s F-measure of 18.8 %.