Pith. sign in

REVIEW 1 cited by

Context-Aware Cross-Attention for Non-Autoregressive Translation

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 2011.00770 v1 pith:A4XBTGPT submitted 2020-11-02 cs.CL

classification cs.CL
keywords cross-attentionsourcetranslationnon-autoregressiveproblemprocesstargetaccelerates
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence. However, due to the lack of target dependency modelling in the decoder, the conditional generation process heavily depends on the cross-attention. In this paper, we reveal a localness perception problem in NAT cross-attention, for which it is difficult to adequately capture source context. To alleviate this problem, we propose to enhance signals of neighbour source tokens into conventional cross-attention. Experimental results on several representative datasets show that our approach can consistently improve translation quality over strong NAT baselines. Extensive analyses demonstrate that the enhanced cross-attention achieves better exploitation of source contexts by leveraging both local and global information.

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. Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing

    q-bio.BM 2025-06 conditional novelty 5.0 of 10

    RefineNovo, a non-autoregressive peptide sequencing model with CTC-based curriculum masking and iterative refinement, reports state-of-the-art amino acid precision and peptide recall on the 9-species benchmarks.

Pith tools