Pith. sign in

REVIEW 1 cited by

Exploiting Cross-Sentence Context for Neural Machine Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1704.04347 v3 pith:NNBSK267 submitted 2017-04-14 cs.CL

Longyue Wang , Zhaopeng Tu , Andy Way , Qun Liu This is my paper · ORCID
classification cs.CL
keywords translationapproachcontextcross-sentencedecoderhistoricalmachineneural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on the performance of neural machine translation (NMT). First, this history is summarized in a hierarchical way. We then integrate the historical representation into NMT in two strategies: 1) a warm-start of encoder and decoder states, and 2) an auxiliary context source for updating decoder states. Experimental results on a large Chinese-English translation task show that our approach significantly improves upon a strong attention-based NMT system by up to +2.1 BLEU points.

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. Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding

    cs.CL 2019-08 conditional novelty 5.0 of 10

    Context-aware sentence encoding and bidirectional document encoding improve HAN accuracy by up to 0.46 percentage points on three document classification benchmarks.

Pith tools