Word alignment is the problem of annotating parallel text with translational correspondence. Previous generative word alignment models have made structural assumptions such as the...
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...
In robotics, recognition of human activity has been used extensively for robot task learning through imitation and demonstration. However, there has not been much work on modeling...
Isabel Serrano Vicente, Ville Kyrki, Danica Kragic...
This paper presents a Named Entity Recognition (NER) method dedicated to process speech transcriptions. The main principle behind this method is to collect in an unsupervised way ...
In the POS tagging task, there are two kinds of statistical models: one is generative model, such as the HMM, the others are discriminative models, such as the Maximum Entropy Mod...