Research map / Architectures and efficiency / RNNs and normalization
To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation
Christian Hadiwinoto, Yang Liu, Hwee Tou Ng
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| Add dependency swap features to the baseline with dependency distortion penalty | Phrase-based SMT · Average | BLEU: 38.05 -> 38.98 | Improved |
| Add dependency swap features to the system with dependency distortion penalty and path features (ablation) | Phrase-based SMT · Average | BLEU: 38.32 -> 39.10 | Improved |
| Add dependency distortion penalty | Phrase-based SMT baseline · Average | BLEU: 37.89 -> 38.05 | Improved |
| Add sparse dependency path features without dependency distortion penalty | Phrase-based SMT baseline · Average | BLEU: 37.89 -> 38.07 | Improved |
| Add sparse dependency path features on top of dependency distortion penalty (ablation) | Phrase-based SMT · Average | BLEU: 38.05 -> 38.32 | Improved |
| Add sparse hierarchical reordering orientation features | Phrase-based SMT baseline · Average | BLEU: 37.89 -> 38.24 | Improved |
| Add dependency swap features to the system with dependency distortion penalty (ablation) | Phrase-based SMT · Average | BLEU: 38.05 -> 38.98 | Improved |
| Add dependency swap features and dependency path features together with dependency distortion penalty | Phrase-based SMT · Average | BLEU: 37.89 -> 39.10 | Improved |
| Add dependency path and other sparse features on top of the system with dependency swap features (ablation) | Phrase-based SMT with dependency swap features · Not specified | BLEU | No clear effect |
Closest papers by meaning
- A Dependency-Based Neural Reordering Model for Statistical Machine Translation (AAAI 2017 · similarity 0.96)
- Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing (AAAI 2025 · similarity 0.89)
- Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information (AAAI 2021 · similarity 0.85)
- Order-Independence Without Fine Tuning (NeurIPS 2024 · similarity 0.85)
- MT-Ranker: Reference-free machine translation evaluation by inter-system ranking (ICLR 2024 · similarity 0.84)
- Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing (AAAI 2025 · similarity 0.82)
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.
