REVIEW 2 cited by
Tree-to-Sequence Attentional Neural Machine 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
Signed reviews
read the original abstract
Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end syntactic NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. Experimental results on the WAT'15 English-to-Japanese dataset demonstrate that our proposed model considerably outperforms sequence-to-sequence attentional NMT models and compares favorably with the state-of-the-art tree-to-string SMT system.
Forward citations
Cited by 2 Pith papers
-
DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums
An encoder-decoder neural network with hierarchical attention predicts breast cancer patients' treatment stage sequences from time-evolving subforum activity graphs, with interpretable attention weights.
-
A Better Way to Attend: Attention with Trees for Video Question Answering
A tree-structured memory network that uses parse trees and distinguishes visual from verbal words improves video question answering accuracy over flat sequence attention baselines.
Discussion (0). Continue with ORCID to comment.