Automatic Evaluation of Local Topic Quality

Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, Jordan Boyd-Graber, Kevin Seppi


Abstract
Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for downstream tasks such as classification. Even recent models, which aim to improve the quality of these token-level topic assignments, have been evaluated only with respect to global metrics. We propose a task designed to elicit human judgments of token-level topic assignments. We use a variety of topic model types and parameters and discover that global metrics agree poorly with human assignments. Since human evaluation is expensive we propose a variety of automated metrics to evaluate topic models at a local level. Finally, we correlate our proposed metrics with human judgments from the task on several datasets. We show that an evaluation based on the percent of topic switches correlates most strongly with human judgment of local topic quality. We suggest that this new metric, which we call consistency, be adopted alongside global metrics such as topic coherence when evaluating new topic models.
Anthology ID:
P19-1076
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
788–796
Language:
URL:
https://aclanthology.org/P19-1076
DOI:
10.18653/v1/P19-1076
Bibkey:
Cite (ACL):
Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, Jordan Boyd-Graber, and Kevin Seppi. 2019. Automatic Evaluation of Local Topic Quality. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 788–796, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Automatic Evaluation of Local Topic Quality (Lund et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1076.pdf