Pre-Translation for Neural Machine Translation

By Jan Niehues, Eunah Cho, Thanh-Le Ha, A. Waibel. 2016

94 citations recorded by the source corpus.

Recently, the development of neural machine translation (NMT) has significantly improved the translation quality of automatic machine translation. While most sentences are more accurate and fluent than translations by statistical machine translation (SMT)-based systems, in some cases, the NMT system produces translations that have a completely different meaning. This is especially the case when rare words occur. When using statistical machine translation, it has already been shown that significant gains can be achieved by simplifying the input in a preprocessing step. A commonly used example is the pre-reordering approach. In this work, we used phrase-based machine translation to pre-translate the input into the target language. Then a neural machine translation system generates the final hypothesis using the pre-translation. Thereby, we use either only the output of the phrase-based machine translation (PBMT) system or a combination of the PBMT output and the source sentence. We evaluate the technique on the English to German translation task. Using this approach we are able to outperform the PBMT system as well as the baseline neural MT system by up to 2 BLEU points. We analyzed the influence of the quality of the initial system on the final result.

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

In Natural Language Processing

Citations in the corpus

Retrieve and Refine: Improved Sequence Generation Models For Dialogue (2018, methodology): “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.”
Stronger Baselines for Trustable Results in Neural Machine Translation (2017, methodology): “Input for the neural system is the original source sentence concatenated with the PBMT output (Niehues et al., 2016).”
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.”
Gender Bias in Machine Translation (2021, background): “For instance, current systems segment text into subword units with statistical methods that can break the morphological structure of words, thus losing relevant semantic and syntactic information in morphologically rich languages (Niehues et al., 2016; Ataman et al., 2017).”
Neural Machine Translation: A Review (2019, methodology): “NMT and SMT can also be combined in a cascade, with SMT providing the input to a post-processing NMT system (Niehues et al., 2016; Zhou et al., 2017) or vice versa (Du & Way, 2017).”
The MeMAD Submission to the WMT18 Multimodal Translation Task (2018, methodology): “In the second model, attention takes care of learning how to use the additional information and previous work has shown that this, indeed, is possible (Niehues et al., 2016; Östling et al., 2017).”
The University of Cambridge’s Machine Translation Systems for WMT18 (2018, background): “We use the beam search strategy with beam size 8 of the SGNMT decoder (Stahlberg et al., 2017b, 2018) in all our experiments.”
Neural Networks for Modeling Source Code Edits (2018, background): “The structured objects could be images (Gregor et al., 2015; Denton et al., 2015; Karras et al., 2018), translations (Li et al., 2017; Novak et al., 2016; Niehues et al., 2016; Lee et al., 2018), or source code (Gupta et al., 2017; Shin et al., 2018).”