Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation
Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, Giuseppe Carenini
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.- Anthology ID:
- 2022.emnlp-main.694
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10189–10204
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.694
- DOI:
- 10.18653/v1/2022.emnlp-main.694
- Cite (ACL):
- Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, and Giuseppe Carenini. 2022. Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10189–10204, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation (Li et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.694.pdf