CUNI System for WMT17 Automatic Post-Editing Task

Proceedings of the Conference on Machine Translation (WMT), Volume 2: Shared Task Papers, pages 661–666 Copenhagen, Denmark, September 711, 2017. c⃝2017 Association for Computational Linguistics CUNI System for WMT17 Automatic Post-Editing Task Duˇsan Variˇs and Ondˇrej Bojar Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics, Malostransk´e n´amˇest´ı 25, 118 00 Prague, Czech Republic {varis,bojar}@ufal.mff.cuni.cz Abstract Following upon the last year’s CUNI sys- tem for automatic post-editing of machine translation output, we focus on exploit- ing the potential of sequence-to-sequence neural models for this task. In this sys- tem description paper, we compare sev- eral encoder-decoder architectures on a smaller-scale models and present the sys- tem we submitted to WMT 2017 Auto- matic Post-Editing shared task based on this preliminary comparison. We also show how simple inclusion of synthetic data can improve the overall performance as measured by an automatic evaluation metric. Lastly, we list few example out- puts generated by our post-editing system. 1 Introduction Even with the recent substantial improvements of the machine translation (MT) quality mainly thanks to the increasingly popular neural models (neural MT, NMT), many errors still remain in the output require further post-editing. This can be done manually, or as the automatic post-editing (APE) task expects, automatically. When phrase-based machine translation (PBMT) was the indisputable state of the art, some automatic post-editing (APE) systems were based on the PBMT techniques (Simard et al., 2007). With source-sentence information (B´echara et al., 2011), post-editing results were quite promising. It is therefore not surprising that with the rise of the neural machine transla- tion, neural APE systems based on the findings in NMT research were built (Pal et al., 2016) and even won last year’s WMT16 Shared Task (Junczys-Dowmunt and Grundkiewicz, 2016). In this paper, we present a baseline comparison of several recent neural sequence-to-sequence ar- chitectures, motivations behind our primary sub- mission for the WMT17 Shared Task and further improvements of this submission with regard to model size and additional synthetic data. 2 Experiments In automatic post-editing, we are expected to take the output of an MT system that usually contains various errors (morphological, lexical etc.) and to generate a corrected version of the output. Most of the time, there is also additional information avail- able, e.g. the original sentence in the source lan- guage and sometimes also some internal scores or features from the primary MT system. 2.1 Examined Setups If we look at the recent developments in the field of NMT, we can see that there are many differ- ent novel approaches that often bring significant improvements to the overall performance of the NMT system. It is natural to ask how these find- ings can be applied to APE task and how much they can contribute to the APE system perfor- mance. We experimented in two areas: (1) how to feed simultaneously the source sentence and the MT output (multi-source input), and (2) whether to use subword units or individual characters. 2.1.1 Multi-Source Input All our experiments use both the …

Content truncated to 500 words