Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling

Aaron Mueller, Mark Dredze


Abstract
Neural topic models can augment or replace bag-of-words inputs with the learned representations of deep pre-trained transformer-based word prediction models. One added benefit when using representations from multilingual models is that they facilitate zero-shot polylingual topic modeling. However, while it has been widely observed that pre-trained embeddings should be fine-tuned to a given task, it is not immediately clear what supervision should look like for an unsupervised task such as topic modeling. Thus, we propose several methods for fine-tuning encoders to improve both monolingual and zero-shot polylingual neural topic modeling. We consider fine-tuning on auxiliary tasks, constructing a new topic classification task, integrating the topic classification objective directly into topic model training, and continued pre-training. We find that fine-tuning encoder representations on topic classification and integrating the topic classification task directly into topic modeling improves topic quality, and that fine-tuning encoder representations on any task is the most important factor for facilitating cross-lingual transfer.
Anthology ID:
2021.naacl-main.243
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3054–3068
Language:
URL:
https://aclanthology.org/2021.naacl-main.243
DOI:
10.18653/v1/2021.naacl-main.243
Bibkey:
Cite (ACL):
Aaron Mueller and Mark Dredze. 2021. Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3054–3068, Online. Association for Computational Linguistics.
Cite (Informal):
Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling (Mueller & Dredze, NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.243.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.243.mp4
Code
 aaronmueller/contextualized-topic-models
Data
MLDocMultiNLISNLI