Words in Chinese text are not naturally separated by delimiters, which poses a challenge to standard machine translation (MT) systems. In MT, the widely used approach is to apply ...
Jia Xu, Jianfeng Gao, Kristina Toutanova, Hermann ...
This paper first describes an experiment to construct an English-Chinese parallel corpus, then applying the Uplug word alignment tool on the corpus and finally produce and evaluat...
We examine the problem of overcoming noisy word-level alignments when learning tree-to-string translation rules. Our approach introduces new rules, and reestimates rule probabilit...
A bitext, or bilingual parallel corpus, consists of two texts, each one in a different language, that are mutual translations. Bitexts are very useful in linguistic engineering bec...
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...