Improving Translation Model by Monolingual Data

By Ondrej Bojar, Ales Tamchyna. 2011

97 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Beyond English-Centric Multilingual Machine Translation (2020, background): “Backtranslation (BT) creates synthetic bitexts from unaligned monolingual data (Schwenk, 2008; Bojar and Tamchyna, 2011; Sennrich et al., 2016a; Edunov et al., 2018; Hoang et al., 2018).”
Tagged Back-Translation (2019, methodology): “Back-translation was originally introduced for phrase-based systems (Bertoldi and Federico, 2009; Bojar and Tamchyna, 2011), but flourished in NMT after work by Sennrich et al.”
Self-training Improves Pre-training for Natural Language Understanding (2020, background): “, 2020) and back-translation for machine translation (Bojar and Tamchyna, 2011; Sennrich et al., 2015; Edunov et al., 2018), assumes the existence of unannotated data in the same domain as the downstream task.”
Unsupervised Speech Recognition (2021, methodology): “Other work explored data augmentation via a technique similar to back-translation (Hayashi et al., 2018) as used in machine translation (Bojar and Tamchyna, 2011; Sennrich et al., 2015; Edunov et al., 2018).”
Iterative Back-Translation for Neural Machine Translation (2018, methodology): “The idea of back-translation dates back at least to statistical machine translation, where it has been used for semi-supervised learning (Bojar and Tamchyna, 2011), or self-training (Goutte et al.”
Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting (2019, background): “In addition to word substitution (Fadaee et al., 2017; Zhou et al., 2019) and paraphrasing (Dong et al., 2017), back translation (Bojar and Tamchyna, 2011; Sennrich et al., 2016a) including its variations (He et al., 2016; Zhang et al., 2018) at-tracts much attention as its success in MT (Ponce-las…”
Chimera – Three Heads for English-to-Czech Translation (2013, background): “(7)We are aware of the fact that Moses alternative decoding paths (Birch and Osborne, 2007) with similar phrase tables clutter n-best lists with identical items, making MERT less stable (Eisele et al., 2008; Bojar and Tamchyna, 2011).”
Abstract Text Summarization: A Low Resource Challenge (2019, unknown): “The use of synthetic data along with the real data is one of the popular approaches followed in machine translation domain for the low resource conditions to improve the translation quality (Bojar and Tamchyna, 2011; Hoang et al., 2018; ChineaRıos et al., 2017).”
DUB: Discrete Unit Back-translation for Speech Translation (2023, methodology): “This approach has been shown to be effective in both statistical (Bertoldi and Fed-erico, 2009; Bojar and Tamchyna, 2011) and neural machine translation models (Sennrich et al., 2016; Edunov et al., 2018; Hoang et al., 2018), and is frequently used to improve translation performance in WMT…”
Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM (2023, unknown): “A last point worth mentioning is that prompting with monolingual data hurts performance, but that using pseudo-parallel data obtained with back-translation (Bojar and Tamchyna, 2011) is an effective workaround.”
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020, background): “This is a popular approach in machine translation where target sentences are back-translated into source sentences (Bojar and Tamchyna, 2011; Hoang et al., 2018).”
Investigating Backtranslation in Neural Machine Translation (2018, result): “Note too that in contrast to the efforts of Rarrick et al. [2011], backtranslation has been applied successfully in PBSMT. Bojar and Tamchyna [2011] use back-translated data to optimize the translation model of a PBSMT system and show improvements in the overall translation quality for 8 language pa”
Modeling Target-Side Inflection in Neural Machine Translation (2017, background): “Another successful attempt to learn novel in-ﬂections in SMT is back-translation (Bojar and Tamchyna, 2011).”
CUNI Submissions in WMT18 (2018, methodology): “Bojar and Tamchyna (2011) explain how back-translation (with some fall-back for unknown words) allows to improve the vocabulary when tar-getting morphologically rich languages.”
Findings of the 2011 Workshop on Statistical Machine Translation (2011, background): “, 2011) CU-TAMCHYNA Charles University - Tamchyna (Bojar and Tamchyna, 2011) CU-ZEMAN Charles University - Zeman (Zeman, 2011) DFKI-FEDERMANN Deutsches Forschungszentrum für Künstliche Intelligenz - Federmann (Federmann and Hunsicker, 2011) DFKI-XU Deutsches Forschungszentrum für Künstliche Intellig”