Research map / Architectures and efficiency / RNNs and normalization
Asynchronous Bidirectional Decoding for Neural Machine Translation
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add a backward decoder and let the forward decoder attend to its reverse hidden states | Attentional encoder-decoder NMT · NIST Chinese-English | BLEU: +3.14 BLEU points | Helped |
| Add a backward decoder and let the forward decoder attend to its reverse hidden states | Attentional encoder-decoder NMT · WMT English-German | BLEU | Helped |
| Attend jointly to reverse hidden states in an end-to-end model rather than use bidirectional k-best rescoring | NIST Chinese-English NMT · NIST Chinese-English | BLEU: +1.86 BLEU points | Helped |
| Use reverse hidden-state representations instead of the best reverse translation | NSC · NIST Chinese-English | BLEU | Helped |
Closest papers by meaning
- Regularizing Neural Machine Translation by Target-Bidirectional Agreement (AAAI 2019 · similarity 0.90)
- Multi-Channel Encoder for Neural Machine Translation (AAAI 2018 · similarity 0.89)
- Neural Machine Translation with Joint Representation (AAAI 2020 · similarity 0.89)
- Neural Machine Translation with Reconstruction (AAAI 2017 · similarity 0.88)
- Non-autoregressive Machine Translation with Disentangled Context Transformer (ICML 2020 · similarity 0.88)
- Syntax-Directed Attention for Neural Machine Translation (AAAI 2018 · similarity 0.88)
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.