Pith. sign in

REVIEW 1 cited by

Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

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 2109.05853 v1 pith:EIDHJ4JR submitted 2021-09-13 cs.CL cs.AI

Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

classification cs.CL cs.AI
keywords attentionweightsalignmentalignmentsanalysisencoder-decoderlargelymechanism
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment errors by relying mainly on uninformative tokens from the source sequence. However, we observe that NMT models assign attention to these tokens to regulate the contribution in the prediction of the two contexts, the source and the prefix of the target sequence. We provide evidence about the influence of wrong alignments on the model behavior, demonstrating that the encoder-decoder attention mechanism is well suited as an interpretability method for NMT. Finally, based on our analysis, we propose methods that largely reduce the word alignment error rate compared to standard induced alignments from attention weights.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models

    cs.LG 2025-08 unverdicted novelty 3.0

    A systematic literature review of explainability in multimodal attention models finds most studies focus on vision-language tasks with attention-based explanations, but evaluation methods lack consistency and modality...