Using monolingual source-language data to improve MT performance

By Nicola Ueffing. 2006

48 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 Machine Translation

Citations in the corpus

Improving Gender Translation Accuracy with Filtered Self-Training (2021, unknown): “Self-Training for MT: Monolingual data has been exploited via self-training methods to enhance statistical MT (Schwenk, 2008; Ueffing, 2006) as well as neural MT (Wu et al.”
Facebook AI’s WAT19 Myanmar-English Translation Task Submission (2019, background): “We investigated the use of selftraining (Yarowski, 1995; Ueffing, 2006; Zhang and Zong, 2016; He et al., 2019) which augments”
Investigations on large-scale lightly-supervised training for statistical machine translation. (2008, methodology): “It is only possible to learn longer phrases of already existing words in the phrase table or to modify the probabilities of existing phrase pairs [ 9 ].”
slimIPL: Language-Model-Free Iterative Pseudo-Labeling (2020, background): “Many recent works on self-training propose and validate these extensions, including those in computer vision [12, 13], natural language processing [14, 15, 16, 17, 18, 19, 20], ASR [21, 7, 22, 8, 9], and speech translation [23].”
Investigations on Translation Model Adaptation Using Monolingual Data (2011, unknown): “In comparison to self enhancing as proposed by Uefﬁng (2006), lightly-supervised training does not adapt itself to the test data, but large amounts of monolingual training data are translated and a completely new model is built.”
Facebook AI’s WMT20 News Translation Task Submission (2020, methodology): “Self-training (Ueffing, 2006; Zhang and Zong, 2016; He et al., 2019) is a method that leverage monolingual data in source language to improve the system performance.”
Transductive learning for statistical machine translation (2007, methodology): “For an analysis of the self-trained phrase tables, examples of translated sentences, and the phrases used in translation, see (Uefﬁng, 2006).”
Semi-supervised model adaptation for statistical machine translation (2007, background): “We provide a basic description here; for a detailed description see Ueffing et al. (2007). The models (or features) which are employed by the decoder are:”