Research map / Label-efficient and robust learning / Recognition and long-tail
Improved English to Russian Translation by Neural Suffix Prediction
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 separate stem and suffix prediction | RNN-based NMT · News2014 | BLEU: 19.72 -> 21.30 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · News2015 | BLEU: 16.11 -> 18.09 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · News2016 | BLEU: 15.41 -> 17.09 | Helped |
| Add separate stem and suffix prediction | Transformer · News2014 | BLEU: 23.18 -> 24.41 | Helped |
| Add separate stem and suffix prediction | Transformer · News2015 | BLEU: 18.66 -> 20.54 | Helped |
| Add separate stem and suffix prediction | Transformer · News2016 | BLEU: 18.31 -> 19.62 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · Title | BLEU: 17.52 -> 17.85 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · Offer | BLEU: 29.78 -> 30.60 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · Comments | BLEU: 33.29 -> 34.18 | Helped |
| Add separate stem and suffix prediction | RNN-based NMT · News2014 | Stem BLEU: 22.59 -> 26.22 | Helped |
Closest papers by meaning
- Improved Neural Machine Translation with SMT Features (AAAI 2016 · similarity 0.88)
- A Latent Morphology Model for Open-Vocabulary Neural Machine Translation (ICLR 2020 · similarity 0.88)
- Neural Machine Translation Advised by Statistical Machine Translation (AAAI 2017 · similarity 0.87)
- From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables (AAAI 2022 · similarity 0.87)
- Neural Machine Translation with Reconstruction (AAAI 2017 · similarity 0.86)
- Unsupervised Neural Machine Translation (ICLR 2018 · similarity 0.86)
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.