exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models

Benjamin Hoover, Hendrik Strobelt, Sebastian Gehrmann


Abstract
Large Transformer-based language models can route and reshape complex information via their multi-headed attention mechanism. Although the attention never receives explicit supervision, it can exhibit recognizable patterns following linguistic or positional information. Analyzing the learned representations and attentions is paramount to furthering our understanding of the inner workings of these models. However, analyses have to catch up with the rapid release of new models and the growing diversity of investigation techniques. To support analysis for a wide variety of models, we introduce exBERT, a tool to help humans conduct flexible, interactive investigations and formulate hypotheses for the model-internal reasoning process. exBERT provides insights into the meaning of the contextual representations and attention by matching a human-specified input to similar contexts in large annotated datasets. By aggregating the annotations of the matched contexts, exBERT can quickly replicate findings from literature and extend them to previously not analyzed models.
Anthology ID:
2020.acl-demos.22
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Month:
July
Year:
2020
Address:
Online
Editors:
Asli Celikyilmaz, Tsung-Hsien Wen
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
187–196
Language:
URL:
https://aclanthology.org/2020.acl-demos.22
DOI:
10.18653/v1/2020.acl-demos.22
Bibkey:
Cite (ACL):
Benjamin Hoover, Hendrik Strobelt, and Sebastian Gehrmann. 2020. exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 187–196, Online. Association for Computational Linguistics.
Cite (Informal):
exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models (Hoover et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-demos.22.pdf
Video:
 http://slideslive.com/38928606