Pith. sign in

REVIEW 1 cited by

Understanding Multi-Head Attention in Abstractive Summarization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.03898 v1 pith:PKSE4PPA submitted 2019-11-10 cs.CL cs.LG

classification cs.CLcs.LG
keywords headsattentionfindpruningsummarizationabstractiveactivationarchitectures
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision Models

    cs.CL 2025-04 conditional novelty 3.0 of 10

    A survey that organizes PEFT methods into additive, selective, reparameterized, hybrid, and unified families, but with no new method or verified experiments.

Pith tools