Darren Scott Appling

Also published as: Darren Scott Appling


pdf bib
Improving statistical machine translation by paraphrasing the training data.
Francis Bond | Eric Nichols | Darren Scott Appling | Michael Paul
Proceedings of the 5th International Workshop on Spoken Language Translation: Papers

Large amounts of training data are essential for training statistical machine translations systems. In this paper we show how training data can be expanded by paraphrasing one side. The new data is made by parsing then generating using a precise HPSG based grammar, which gives sentences with the same meaning, but minor variations in lexical choice and word order. In experiments with Japanese and English, we showed consistent gains on the Tanaka Corpus with less consistent improvement on the IWSLT 2005 evaluation data.


pdf bib
Combining resources for open source machine translation
Eric Nichols | Francis Bond | Darren Scott Appling | Yuji Matsumoto
Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages: Papers