DeepAI AI Chat
Log In Sign Up

Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

by   Hendrik Strobelt, et al.

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.


page 2

page 6

page 8


Sequence-to-sequence neural network models for transliteration

Transliteration is a key component of machine translation systems and so...

Improving Conditioning in Context-Aware Sequence to Sequence Models

Neural sequence to sequence models are well established for applications...

Sequence-to-Sequence Learning as Beam-Search Optimization

Sequence-to-Sequence (seq2seq) modeling has rapidly become an important ...

Interactive-predictive neural multimodal systems

Despite the advances achieved by neural models in sequence to sequence l...

A Deep Learning Based Chatbot for Campus Psychological Therapy

In this paper, we propose Evebot, an innovative, sequence to sequence (S...

Do RNN States Encode Abstract Phonological Processes?

Sequence-to-sequence models have delivered impressive results in word fo...

Predicting the time-evolution of multi-physics systems with sequence-to-sequence models

In this work, sequence-to-sequence (seq2seq) models, originally develope...