0

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

A human-in-the-loop pipeline is used to discover and inject task-specific attention patterns into transformer models, improving their accuracy and efficiency.

Year
2021
Venue
arXiv 2021
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2112.05364v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers propose new attention augmentation methods to make transformers more accurate, efficient and interpretable. In this paper, we combine these two lines of research in a human-in-the-loop pipeline to first discover important task-specific attention patterns. Then those patterns are injected, not only to smaller models, but also to the original model. The benefits of our pipeline and discovered patterns are demonstrated in two case studies with extractive summarization and topic segmentation. After discovering interpretable patterns in BERT-based models fine-tuned for the two downstream tasks, experiments indicate that when we inject the patterns into attention heads, the models show considerable improvements in accuracy and efficiency.

Authors

6