Syntax-based Rewriting for Simultaneous Machine Translation
By He He, Alvin Grissom II, John Morgan, Jordan L. Boyd-Graber, Hal Daumé Iii. 2015
37 citations recorded by the source corpus.
Divergent word order between languages causes delay in simultaneous machine translation. We present a sentence rewriting method that generates more monotonic translations to improve the speedaccuracy tradeoff. We design grammaticality and meaning-preserving syntactic transformation rules that operate on constituent parse trees. We apply the rules to reference translations to make their word order closer to the source language word order. On Japanese-English translation (two languages with substantially different structure), incorporating the rewritten, more monotonic reference translation into a phrase-based machine translation system enables better translations faster than a baseline system that only uses gold reference translations.
Subfields: Artificial Intelligence, Machine Translation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jordan L. Boyd-Graber
- Hal Daumé Iii
- Graham Neubig
- Noah A. Smith
- He He
- Haifeng Wang
- Hua Wu
- Jianfeng Gao
In Machine Translation
- Jordan L. Boyd-Graber
- He He
- Khanh Nguyen
- Hal Daumé Iii
- Hua Wu
- Jörg Tiedemann
- Preslav Nakov
- Desmond Elliott
Citations in the corpus
- Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback (2017, background): “, 2014) and reordering (He et al., 2015) among other strategies to both minimize delay and effectively translate a sentence (He et al.”
- STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (2018, background): “…latency by explicitly predicting the sentencefinal German (Grissom II et al., 2014) or English verbs (Matsubarayx et al., 2000), which is limited to this particular case, or unseen syntactic constituents (Oda et al., 2015; He et al., 2015), which requires incremental parsing on the source sentence.”
- Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation (2016, background): “He et al. (2015) use hand-crafted rules to decrease latency; our data-driven approach could yield additional strategies for improving MT systems.”