SEQ2SEQ-VIS : A Visual Debugging Tool for Sequence-to-Sequence Models.
IEEE Trans Vis Comput Graph
; 2018 Oct 17.
Article
em En
| MEDLINE
| ID: mdl-30334796
ABSTRACT
Neural sequence-to-sequence models have proven to be accurate and robust for many sequence prediction tasks, and have become the standard approach for automatic translation of text. The models work with a five-stage blackbox pipeline that begins with encoding a source sequence to a vector space and then decoding out to a new target sequence. This process is now standard, but like many deep learning methods remains quite difficult to understand or debug. In this work, we present a visual analysis tool that allows interaction and "what if"-style exploration of trained sequence-to-sequence models through each stage of the translation process. The aim is to identify which patterns have been learned, to detect model errors, and to probe the model with counterfactual scenario. We demonstrate the utility of our tool through several real-world sequence-to-sequence use cases on large-scale models.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
IEEE Trans Vis Comput Graph
Assunto da revista:
INFORMATICA MEDICA
Ano de publicação:
2018
Tipo de documento:
Article