The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
By Felix Stahlberg, Eva Hasler, Bill Byrne. 2016
7 citations recorded by the source corpus.
This paper presents the University of Cambridge submission to WMT16. Motivated by the complementary nature of syntactical machine translation and neural machine translation (NMT), we exploit the synergies of Hiero and NMT in different combination schemes. Starting out with a simple neural lattice rescoring approach, we show that the Hiero lattices are often too narrow for NMT ensembles. Therefore, instead of a hard restriction of the NMT search space to the lattice, we propose to loosely couple NMT and Hiero by composition with a modified version of the edit distance transducer. The loose combination outperforms lattice rescoring, especially when using multiple NMT systems in an ensemble.
Subfields: Artificial Intelligence, Natural Language Processing
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
- Felix Stahlberg
- Peter J. Liu
- Quoc V. Le
- Prajit Ramachandran
- Mohit Bansal
- Jianfeng Gao
- Furu Wei
- Kyunghyun Cho
In Natural Language Processing
- Felix Stahlberg
- Peter J. Liu
- Quoc V. Le
- Mohit Bansal
- Furu Wei
- Kyunghyun Cho
- Mirella Lapata
- Jianfeng Gao
Citations in the corpus
- Unsupervised Pretraining for Sequence to Sequence Learning (2016, background): “4 Edit Distance Transducer NMT (Stahlberg et al., 2016) single 21.”
- Neural Machine Translation: A Review (2019, methodology): “Popular examples in this category are rescoring and reranking methods (Neubig et al., 2015; Stahlberg et al., 2016; Khayrallah et al., 2017; Grundkiewicz & Junczys-Dowmunt, 2018; Avramidis et al., 2016; Marie & Fujita, 2018; Zhang et al., 2017), although these models may be too constraining if the n”