LGCLNEJun 5, 2015

Visualizing and Understanding Recurrent Networks

arXiv:1506.02078v21138 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the lack of interpretability in LSTMs for researchers and practitioners, though it is incremental as it builds on existing models without introducing new methods.

The paper tackled the problem of understanding why Long Short-Term Memory (LSTM) recurrent neural networks perform well on sequential data by analyzing their representations and errors using character-level language models, revealing interpretable cells that track long-range dependencies like line lengths and brackets.

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data. However, while LSTMs provide exceptional results in practice, the source of their performance and their limitations remain rather poorly understood. Using character-level language models as an interpretable testbed, we aim to bridge this gap by providing an analysis of their representations, predictions and error types. In particular, our experiments reveal the existence of interpretable cells that keep track of long-range dependencies such as line lengths, quotes and brackets. Moreover, our comparative analysis with finite horizon n-gram models traces the source of the LSTM improvements to long-range structural dependencies. Finally, we provide analysis of the remaining errors and suggests areas for further study.

Code Implementations3 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes