Data augmentation and language model adaptation

Janiszek, David; Mori, Renato De; Bechet, E.

doi:10.1109/icassp.2001.940890

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the current study we modify the target language model P(t), to represent the test data better, and thereby improve the translation quality. (Janiszek, et al 2001) list the following approaches to language model adaptation:…”

Section: Introductionmentioning

confidence: 99%

Language model adaptation for statistical machine translation with structured query models

Zhao

Eck

Vogel

2004

Proceedings of the 20th International Conference on Computational Linguistics - COLING '04

View full text Add to dashboard Cite

We explore unsupervised language model adaptation techniques for Statistical Machine Translation. The hypotheses from the machine translation output are converted into queries at different levels of representation power and used to extract similar sentences from very large monolingual text collection. Specific language models are then build from the retrieved data and interpolated with a general background model. Experiments show significant improvements when translating with these adapted language models.

show abstract

Section: Introductionmentioning

confidence: 99%

Language model adaptation for statistical machine translation with structured query models

Zhao

Eck

Vogel

2004

Proceedings of the 20th International Conference on Computational Linguistics - COLING '04

View full text Add to dashboard Cite

show abstract

“…For example, it is possible to leverage document retrieval techniques to increase the size of A by dynamically searching online databases or the world wide web (Berger and Miller, 1998;Iyer and Ostendorf, 1999;Zhu and Rosenfeld, 2001). Alternatively, data augmentation can also be performed at the n-gram count rather than the word level: a preliminary investigation along these lines was recently reported in (Janiszek et al, 2001). Ultimately, some form of data updating has to be entertained, to counteract the inability of any corpus to reflect events which postdate it.…”

Section: Adaptation Datamentioning

confidence: 99%