Publication Type
Journal Article
Version
publishedVersion
Publication Date
9-2024
Abstract
Automated coherence metrics constitute an efficient and popular way to evaluate topic models. Previous work presents a mixed picture of their presumed correlation with human judgment. This work proposes a novel sampling approach to mining topic representations at a large scale while seeking to mitigate bias from sampling, enabling the investigation of widely used automated coherence metrics via large corpora. Additionally, this article proposes a novel user study design, an amalgamation of different proxy tasks, to derive a finer insight into the human decision-making processes. This design subsumes the purpose of simple rating and outlier-detection user studies. Similar to the sampling approach, the user study conducted is extensive, comprising 40 study participants split into eight different study groups tasked with evaluating their respective set of 100 topic representations. Usually, when substantiating the use of these metrics, human responses are treated as the gold standard. This article further investigates the reliability of human judgment by flipping the comparison and conducting a novel extended analysis of human response at the group and individual level against a generic corpus. The investigation results show a moderate to good correlation between these metrics and human judgment, especially for generic corpora, and derive further insights into the human perception of coherence. Analyzing inter-metric correlations across corpora shows moderate to good correlation among these metrics. As these metrics depend on corpus statistics, this article further investigates the topical differences between corpora, revealing nuances in applications of these metrics.
Keywords
Vocabulary, decision-making processes, topic models
Discipline
Computational Engineering | Databases and Information Systems | Linguistics
Research Areas
Data Science and Engineering
Areas of Excellence
Digital transformation
Publication
Computational Linguistics
Volume
50
Issue
3
First Page
893
Last Page
952
ISSN
0891-2017
Identifier
10.1162/coli_a_00518
Publisher
Massachusetts Institute of Technology Press
Citation
LIM, Jia Peng and LAUW, Hady Wirawan.
Aligning human and computational coherence evaluations. (2024). Computational Linguistics. 50, (3), 893-952.
Available at: https://ink.library.smu.edu.sg/sis_research/9427
Copyright Owner and License
Publisher-CC-NC-ND
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1162/coli_a_00518
Included in
Computational Engineering Commons, Databases and Information Systems Commons, Linguistics Commons