Title | ||
---|---|---|
An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing. |
Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2017 | international joint conference on natural language processing | Conference |
Volume | Citations | PageRank |
abs/1706.04138 | 3 | 0.41 |
References | Authors | |
9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcin Junczys-Dowmunt | 1 | 312 | 24.24 |
Roman Grundkiewicz | 2 | 109 | 11.75 |