An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
By Marcin Junczys-Dowmunt, Roman Grundkiewicz. 2017
48 citations recorded by the source corpus.
In this work, we explore multiple neural architectures adapted for the task of automatic post-editing of machine translation output. We focus on neural end-to-end models that combine both inputs mt (raw MT output) and src (source language input) in a single neural architecture, modeling \{mt, src\} \rightarrow pe directly. Apart from that, we investigate the influence of hard-attention models which seem to be well-suited for monolingual tasks, as well as combinations of both ideas. We report results on data sets provided during the WMT-2016 shared task on automatic post-editing and can demonstrate that dual-attention models that incorporate all available data in the APE scenario in a single model improve on the best shared task system and on all other published results after the shared task. Dual-attention models that are combined with hard attention remain competitive despite applying fewer changes to the input.
Subfields: Artificial Intelligence, Information Systems, 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
- Philipp Koehn
- Ondrej Bojar
- Graham Neubig
- Lucia Specia
- Luke S. Zettlemoyer
- Qun Liu
- Kyunghyun Cho
- Felix Stahlberg
In Information Systems
- Philipp Koehn
- Matt Post
- Christof Monz
- Lucia Specia
- Ondrej Bojar
- Barry Haddow
- Yvette Graham
- Matthias Huck
In Natural Language Processing
- Philipp Koehn
- Ondrej Bojar
- Lucia Specia
- Graham Neubig
- Barry Haddow
- Kyunghyun Cho
- Luke S. Zettlemoyer
- Jason Aaron Edward Weston
Citations in the corpus
- Retrieve and Refine: Improved Sequence Generation Models For Dialogue (2018, background): “initial predictions (Junczys-Dowmunt and Grundkiewicz, 2017; Niehues et al., 2016; Novak et al., 2016; Xia et al., 2017; Grangier and Auli, 2017) or combining with retrieval (Gu et al.”
- Findings of the 2017 Conference on Machine Translation (WMT17) (2017, background): “AMU Adam Mickiewicz University, Poland (Junczys-Dowmunt and Grundkiewicz, 2017) CUNI Univerzita Karlova v Praze, Czech Republic (Variš and Bojar, 2017) DCU Dublin City University, Ireland (Hokamp, 2017) FBK Fondazione Bruno Kessler, Italy (Chatterjee et al.”