atlas

Research map / Architectures and efficiency / Attention and transformers

Multi-Channel Encoder for Neural Machine Translation

AAAI 2018 · Architectures and efficiency › Attention and transformers · approach: Efficient language transformers · 28 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
combine embeddings, RNN hidden states, and NTM memory with gated annotationattention-based NMT · NIST Chinese-English (AVG)BLEU: 28.73 -> 35.25Helped
add the embedding annotation channel (ablation)NTM-RNN · NIST Chinese-English (AVG)BLEU: 34.33(+5.60) -> 35.25(+6.52)Helped
add the NTM memory channel (ablation)RNN-EMB · NIST Chinese-English (AVG)BLEU: 34.61(+5.88) -> 35.25(+6.52)Helped
add the RNN hidden-state channel (ablation)NTM-EMB · NIST Chinese-English (AVG)BLEU: 33.75(+5.02) -> 35.25(+6.52)Helped
use embeddings as the only annotation instead of multiple encoding channels (ablation)attention-based NMT · NIST Chinese-English (AVG)BLEU: 19.52Hurt
add all three encoding channelsRNN + BPE-40K · WMT14 English-French (news-test-2014)BLEU: 38.19 -> 38.80Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy