Research map / Architectures and efficiency / RNNs and normalization
A Dependency-Based Neural Reordering Model for Statistical Machine Translation
Christian Hadiwinoto, Hwee Tou Ng
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Replace sparse dependency swap features with a 10-system neural reordering ensemble initialized with dependency-driven embeddings | Phrase-based Chinese-to-English SMT · NIST average | BLEU: +0.57 BLEU point | Improved |
| Replace sparse dependency swap features with a single neural classifier initialized with dependency-driven embeddings | Phrase-based Chinese-to-English SMT · NIST average | BLEU: +0.32 BLEU point | Improved |
| Add dependency-driven word embedding initialization (ablation) | Neural reordering classifier · NIST average | BLEU: 39.06 -> 39.55 | Improved |
| Replace dependency-driven embeddings with random initialization (ablation) | Neural reordering classifier · NIST average | BLEU: 39.55 -> 38.12 | Hurt |
| Replace dependency-driven embeddings with skip-gram embeddings (ablation) | Neural reordering classifier · NIST average | BLEU: 39.55 -> 39.06 | No clear effect |
| Use a 10-system ensemble instead of a single neural classifier (ablation) | Dependency-driven neural reordering · NIST average | BLEU: 39.30 -> 39.55 | Improved |
| Add neural reordering without conventional phrase-based reordering models (ablation) | Phrase-based Chinese-to-English SMT · NIST average | BLEU: +1.05 BLEU point | Improved |
| Use sparse dependency distortion and swap features without conventional phrase-based reordering models (ablation) | Phrase-based Chinese-to-English SMT · NIST average | BLEU: 37.74 vs 37.89 | Hurt |
Closest papers by meaning
- To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation (AAAI 2016 · similarity 0.96)
- Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing (AAAI 2025 · similarity 0.90)
- Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information (AAAI 2021 · similarity 0.87)
- Order-Independence Without Fine Tuning (NeurIPS 2024 · similarity 0.85)
- Neural Machine Translation with Joint Representation (AAAI 2020 · similarity 0.85)
- MT-Ranker: Reference-free machine translation evaluation by inter-system ranking (ICLR 2024 · similarity 0.84)
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.
