- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Faculty Research and Publications /
- T³-Vis : a visual analytic framework for Training and...
Open Collections
UBC Faculty Research and Publications
T³-Vis : a visual analytic framework for Training and fine-Tuning Transformers in NLP Li, Raymond; Xiao, Wen; Wang, Lanjun; Jang, Hyeju; Carenini, Giuseppe
Abstract
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present the design and implementation of a visual analytic framework for assisting researchers in such process, by providing them with valuable insights about the model’s intrinsic properties and behaviours. Our framework offers an intuitive overview that allows the user to explore different facets of the model (e.g., hidden states, attention) through interactive visualization, and allows a suite of built-in algorithms that compute the importance of model components and different parts of the input sequence. Case studies and feedback from a user focus group indicate that the framework is useful, and suggest several improvements. Our framework is available at: https: //github.com/raymondzmc/T3-Vis.
Item Metadata
Title |
T³-Vis : a visual analytic framework for Training and fine-Tuning Transformers in NLP
|
Creator | |
Date Issued |
2021
|
Description |
Transformers are the dominant architecture in
NLP, but their training and fine-tuning is still
very challenging. In this paper, we present
the design and implementation of a visual analytic framework for assisting researchers in
such process, by providing them with valuable insights about the model’s intrinsic properties and behaviours. Our framework offers
an intuitive overview that allows the user to
explore different facets of the model (e.g., hidden states, attention) through interactive visualization, and allows a suite of built-in algorithms that compute the importance of model
components and different parts of the input
sequence. Case studies and feedback from
a user focus group indicate that the framework is useful, and suggest several improvements. Our framework is available at: https:
//github.com/raymondzmc/T3-Vis.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2022-01-19
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution 4.0 International
|
DOI |
10.14288/1.0406310
|
URI | |
Affiliation | |
Citation |
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 220–230 November 7–11, 2021.
|
Peer Review Status |
Reviewed
|
Scholarly Level |
Faculty; Researcher; Graduate
|
Copyright Holder |
Association for Computational Linguistics
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution 4.0 International