REVIEW 4 cited by
Graph Convolutional Encoders for Syntax-aware 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
We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolutional networks (GCNs), a recent class of neural networks developed for modeling graph-structured data. Our GCNs use predicted syntactic dependency trees of source sentences to produce representations of words (i.e. hidden states of the encoder) that are sensitive to their syntactic neighborhoods. GCNs take word representations as input and produce word representations as output, so they can easily be incorporated as layers into standard encoders (e.g., on top of bidirectional RNNs or convolutional neural networks). We evaluate their effectiveness with English-German and English-Czech translation experiments for different types of encoders and observe substantial improvements over their syntax-agnostic versions in all the considered setups.
Forward citations
Cited by 4 Pith papers
-
Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
A reinforcement-learning graph-to-sequence model with answer-aware alignment reports new state-of-the-art question generation scores on SQuAD, with the gain partly explained by BERT embeddings and direct BLEU-4 optimization.
-
Aligning Linguistic Words and Visual Semantic Units for Image Captioning
VSUA improves image captioning by representing images as graphs of visual semantic units and using context-gated attention to align words with objects, attributes, and relations.
-
Edge-Optimized Deep Learning & Pattern Recognition Techniques for Non-Intrusive Load Monitoring of Energy Time Series
The thesis contributes the Plegma dataset, a 10-second, one-year, 13-house Greek electricity dataset, and shows that lottery-ticket-style pruning before training can shrink NILM models to 5% of their original paramete...
-
Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo
Applying known RNN and transfer-learning methods to English-Igbo yields modest BLEU scores, but the claimed +4.83 BLEU improvement over baselines is inconsistent with the paper's own tables.
Discussion (0). Continue with ORCID to comment.