Investigations on Translation Model Adaptation Using Monolingual Data
By Patrik Lambert, Holger Schwenk, Christophe Servan, Sadaf Abdul Rauf. 2011
63 citations recorded by the source corpus.
Subfields: Natural Language Processing, 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 Natural Language Processing
- Tao Qin
- Tie-Yan Liu
- Philipp Koehn
- Graham Neubig
- Felix Stahlberg
- Holger Schwenk
- Yingce Xia
- David Grangier
In Machine Translation
- David Grangier
- Rui Wang
- Mara Chinea-Rios
- Holger Schwenk
- Christof Monz
- Francisco Casacuberta
- Christophe Servan
- Chenhui Chu
Citations in the corpus
- Tagged Back-Translation (2019, background): “This motivates the use of monolingual data, usually more abundant (Lambert et al., 2011).”
- Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization (2018, methodology): “Specifically, (Bertoldi and Federico 2009; Lambert et al. 2011) have back-translated target-side monolingual data into the sourceside sentence to produce synthetic parallel data for phrasebased SMT.”
- LIUM’s SMT Machine Translation Systems for WMT 2012 (2012, unknown): “A detailed comparison is given in (Lambert et al., 2011).”
- A Survey of Domain Adaptation for Neural Machine Translation (2018, background): “…2016) can be used to score sentences. ii) When there are not enough parallel corpora, there are also studies that generate pseudo-parallel sentences using information retrieval (Utiyama and Isahara, 2003), self-enhancing (Lambert et al., 2011) or parallel word embeddings (Marie and Fujita, 2017).”
- Adapting Neural Machine Translation with Parallel Synthetic Data (2017, methodology): “Other works used target-side corpora to build the synthetic parallel corpus (Bertoldi and Federico, 2009; Lambert et al., 2011).”
- LIUM’s SMT Machine Translation Systems for WMT 2011 (2011, background): “This effect is studied in detail in a separate paper (Lambert et al., 2011).”
- Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation (2018, background): “Lambert et al. (2011) show that adding synthetic source and real target data achieves improvements in traditional phrase-based machine translation (PBMT).”