This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
Inspired by the incremental TER alignment, we re-designed the Indirect HMM (IHMM) alignment, which is one of the best hypothesis alignment methods for conventional MT system combi...
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
Abhishek Arun, Barry Haddow, Philipp Koehn, Adam L...
Web search is challenging partly due to the fact that search queries and Web documents use different language styles and vocabularies. This paper provides a quantitative analysis ...
This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
George Saon, Hagen Soltau, Upendra Chaudhari, Step...