Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
| Autor: | Hanspeter Pfister, Hendrik Strobelt, Michael Behrisch, Alexander M. Rush, Sebastian Gehrmann, Adam Perer |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Artificial Intelligence Computer science Process (engineering) media_common.quotation_subject 02 engineering and technology Machine learning computer.software_genre Data modeling Encoding (memory) 0202 electrical engineering electronic engineering information engineering Neural and Evolutionary Computing (cs.NE) media_common Sequence Computer Science - Computation and Language business.industry Deep learning Computer Science - Neural and Evolutionary Computing 020207 software engineering Computer Graphics and Computer-Aided Design Pipeline (software) Artificial Intelligence (cs.AI) Debugging Signal Processing Computer Vision and Pattern Recognition Artificial intelligence business Computation and Language (cs.CL) computer Software |
| Zdroj: | IEEE Transactions on Visualization and Computer Graphics. 25:353-363 |
| ISSN: | 2160-9306 1077-2626 |
| Popis: | 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 in a five stage blackbox process that involves 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 with a trained sequence-to-sequence model through each stage of the translation process. The aim is to identify which patterns have been learned and to detect model errors. We demonstrate the utility of our tool through several real-world large-scale sequence-to-sequence use cases. VAST - IEEE VIS 2018 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|