Understanding Multi-Head Attention in Abstractive Summarization

By Joris Baan, Maartje ter Hoeve, Marlies van der Wees, Anne Schuth, Maarten de Rijke. 2019

24 citations recorded by the source corpus.

Attention mechanisms in deep learning architectures have often been used as a means of transparency and, as such, to shed light on the inner workings of the architectures. Recently, there has been a growing interest in whether or not this assumption is correct. In this paper we investigate the interpretability of multi-head attention in abstractive summarization, a sequence-to-sequence task for which attention does not have an intuitive alignment role, such as in machine translation. We first introduce three metrics to gain insight in the focus of attention heads and observe that these heads specialize towards relative positions, specific part-of-speech tags, and named entities. However, we also find that ablating and pruning these heads does not lead to a significant drop in performance, indicating redundancy. By replacing the softmax activation functions with sparsemax activation functions, we find that attention heads behave seemingly more transparent: we can ablate fewer heads and heads score higher on our interpretability metrics. However, if we apply pruning to the sparsemax model we find that we can prune even more heads, raising the question whether enforced sparsity actually improves transparency. Finally, we find that relative positions heads seem integral to summarization performance and persistently remain after pruning.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiyuan Liu
2. Minlie Huang
3. Maosong Sun
4. Jie Tang
5. Xu Han
6. Xipeng Qiu
7. Ji-rong Wen
8. Wayne Xin Zhao

Citations in the corpus

• Pre-Trained Models: Past, Present and Future (2021, background): “…shown that the multi-head attention structures are redundant in the tasks of machine translation (Michel et al., 2019), abstractive summarization (Baan et al., 2019), and language understanding (Kovaleva et al., 2019), i.e., when removing part of attention heads, we can achieve better…”
• A Primer in BERTology: What We Know About How BERT Works (2020, background): “, 2019), abstractive summarization (Baan et al., 2019), and GLUE tasks (Kovaleva et al.”