This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to add...
Xiaodong He, Mei Yang, Jianfeng Gao, Patrick Nguye...
Many machine translation (MT) evaluation metrics have been shown to correlate better with human judgment than BLEU. In principle, tuning on these metrics should yield better syste...
Eye tracking experiments have shown that titles of Web search results play a crucial role in guiding a user’s search process. We present a machine-learned algorithm that trains ...
Tapas Kanungo, Nadia Ghamrawi, Ki Yuen Kim, Lawren...
This paper presents a method for cross-language question answering. The method combines multiple query translations in order to improve the answering precision. The combination of ...