The FBK Participation in the WMT15 Automatic Post-editing Shared Task

By Rajen Chatterjee, José G. C. de Souza, Matteo Negri, Marco Turchi. 2015

32 citations recorded by the source corpus.

In this paper, we describe the “FBK EnglishSpanish Automatic Post-editing (APE)” systems submitted to the APE shared task at the WMT 2015. We explore the most widely used statistical APE technique (monolingual) and its most significant variant (context-aware). In this exploration, we introduce some novel task-specific dense features through which we observe improvements over the default setup of these approaches. We show these features are useful to prune the phrase table in order to remove unreliable rules and help the decoder to select useful translation options during decoding. Our primary APE system submitted at this shared task performs significantly better than the standard APE baseline.

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

1. Philipp Koehn
2. Ondrej Bojar
3. Tao Qin
4. Tie-Yan Liu
5. Lucia Specia
6. Graham Neubig
7. Felix Stahlberg
8. Matt Post

In Machine Translation

1. Philipp Koehn
2. Lucia Specia
3. Matt Post
4. Varvara Logacheva
5. Ondrej Bojar
6. Barry Haddow
7. Christian Federmann
8. Matteo Negri

Citations in the corpus

• Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “As pointed out by (Chatterjee et al., 2015b), from the application point of view the task is motivated by its possible uses to: • Improve MT output by exploiting information unavailable to the decoder, or by performing deeper text analysis that is too expensive at the decoding stage; • Cope with…”
• The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task (2016, methodology): “A recent study on APE by Chatterjee et al. (2015b) over six language pairs have reported consistent improvement (7.3% to 14.7% TER reduction) in the quality of machine translated text across all language pairs.”
• Deliberation Networks: Sequence Generation Beyond One-Pass Decoding (2017, background): “One related work is post-editing [16, 2]: a source sentence e is first translated to f ′, and then f ′ is refined by another model.”