2018
EMNLP
EMNLP 2018
An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM
Abstract
AbstractWe present a visualisation tool which aims to illuminate the inner workings of an LSTM model for question answering. It plots heatmaps of neurons’ firings and allows a user to check the dependency between neurons and manual features. The system possesses an interactive web-interface and can be adapted to other models and domains.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Natural Language Processing
📈
Trend Setter
— Question Answering
🧭
Keyword Pioneer
— neural network visualization
🐣
Hot Topic Early Bird
— model interpretability
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio