Research map / Architectures and efficiency / RNNs and normalization
Neural Machine Translation Advised by Statistical 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 SMT recommendations with learned gating | RNNSearch* · NIST Chinese-English test sets | BLEU: 32.50 -> 33.70 | Helped |
| Replace target UNK words using SMT recommendations | RNNSearch* + SMT recommendations · NIST Chinese-English test sets | BLEU: 33.70 -> 34.94 | Helped |
| Add SMT recommendations with learned gating | RNNSearch* · NIST Chinese-English test sets | BLEU: 34.94 vs 32.50 | Helped |
| Add SMT recommendations with learned gating | RNNSearch* · NIST Chinese-English test sets | BLEU: 34.94 vs 31.73 | Helped |
| Add SMT recommendations (ablation) | RNNSearch* + SMT recommendations · NIST Chinese-English test sets | BLEU: 32.50 -> 33.70 | Helped |
| Use flexible gating rather than a fixed gate value of 0.20 (ablation) | RNNSearch* + SMT recommendations · NIST Chinese-English test sets | BLEU: 31.61 -> 33.70 | Helped |
| Use quality SMT recommendations rather than pseudo recommendations (ablation) | RNNSearch* + SMT recommendations · NIST Chinese-English test sets | BLEU: 32.16 -> 33.70 | Helped |
| Add UNK replacement using SMT recommendations | RNNSearch* + SMT recommendations · NIST Chinese-English test sets | BLEU: 33.70 -> 34.94 | Helped |
Closest papers by meaning
- Improved Neural Machine Translation with SMT Features (AAAI 2016 · similarity 0.97)
- Unsupervised Neural Machine Translation with SMT as Posterior Regularization (AAAI 2019 · similarity 0.91)
- Joint Training for Neural Machine Translation Models with Monolingual Data (AAAI 2018 · similarity 0.90)
- Neural Machine Translation with Reconstruction (AAAI 2017 · similarity 0.90)
- Neural Machine Translation with Joint Representation (AAAI 2020 · similarity 0.89)
- Prompting Neural Machine Translation with Translation Memories (AAAI 2023 · similarity 0.89)
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.