SANVis: Visual Analytics for Understanding Self-Attention Networks

Cited 0 time in webofscience Cited 5 time in scopus
  • Hit : 204
  • Download : 0
Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many other applications. Recently, they have been further evolved into an advanced approach called multi-head self-attention networks, which can encode a set of input vectors, e.g., word vectors in a sentence, into another set of vectors. Such encoding aims at simultaneously capturing diverse syntactic and semantic features within a set, each of which corresponds to a particular attention head, forming altogether multi-head attention. Meanwhile, the increased model complexity prevents users from easily understanding and manipulating the inner workings of models. To tackle the challenges, we present a visual analytics system called SANVis, which helps users understand the behaviors and the characteristics of multi-head self-attention networks. Using a state-of-the-art self-attention model called Transformer, we demonstrate usage scenarios of SANVis in machine translation tasks. Our system is available at http://short.sanvis.org.
Publisher
Institute of Electrical and Electronics Engineers Inc.
Issue Date
2019-10
Language
English
Citation

2019 IEEE Visualization Conference, VIS 2019, pp.146 - 150

DOI
10.1109/VISUAL.2019.8933677
URI
http://hdl.handle.net/10203/279874
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0