AI Paper Atlas

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

AAAI 2016 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add dependency swap features to the baseline with dependency distortion penaltyPhrase-based SMT · AverageBLEU: 38.05 -> 38.98Improved
Add dependency swap features to the system with dependency distortion penalty and path features (ablation)Phrase-based SMT · AverageBLEU: 38.32 -> 39.10Improved
Add dependency distortion penaltyPhrase-based SMT baseline · AverageBLEU: 37.89 -> 38.05Improved
Add sparse dependency path features without dependency distortion penaltyPhrase-based SMT baseline · AverageBLEU: 37.89 -> 38.07Improved
Add sparse dependency path features on top of dependency distortion penalty (ablation)Phrase-based SMT · AverageBLEU: 38.05 -> 38.32Improved
Add sparse hierarchical reordering orientation featuresPhrase-based SMT baseline · AverageBLEU: 37.89 -> 38.24Improved
Add dependency swap features to the system with dependency distortion penalty (ablation)Phrase-based SMT · AverageBLEU: 38.05 -> 38.98Improved
Add dependency swap features and dependency path features together with dependency distortion penaltyPhrase-based SMT · AverageBLEU: 37.89 -> 39.10Improved
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 specifiedBLEUNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy