Advances in Statistical Machine Translation in the last 10 years
Place: Large lecture room.
Affiliation: Instituto Politécnico Nacional, Mexico.
My research experience is mainly in Machine Translation (MT), although I have also worked in Automatic Speech Recognition (ASR) and Information Retrieval (IR). In this talk, I will overview several ASR, MT and IR projects that I have participated in and I will introduce my main directions of research in Statistical MT. Statistical MT focuses on finding the most probable translation in the target language given the source language. Challenges in this area cover many areas of natural language processing including language modeling, context information and morphology. Here, I will briefly describe the technology behind the popular phrase-based SMT system and I will cover some of the progress in the area in the last 10 years. Bio Marta Ruiz Costa-jussà is a Telecommunication’s Engineer by the Universitat Politécnica de Catalunya (UPC, Barcelona). She received her PhD from the UPC in 2008. She has worked at LIMSI-CNRS (Paris), Universitat Politècnica de Catalunya (Barcelona), Universitat Pompeu Fabra (Barcelona), Barcelona Media (Barcelona), Universidade de São Paulo (São Paulo), Institute for Infocomm Research (Singapore) and Instituto Politécnico Nacional (Mexico). She has received prestigious and competitive fellowships like: FPU and Juan de la Cierva, BE-DGR (Generalitat de Catalunya), FAPESP Visiting Professor (São Paulo research foundation), an IOF Marie Curie (European Commission) and, recently, a Ramon y Cajal. She has participated in 13 European and National (Spanish, French and Brazilian) projects. She has organized 7 conferences/workshops in the areas of MT and IR, taught several tutorials and seminars, done more than 20 invited talks and published over 100 papers in international scientific journals and conferences receiving several awards. She has been cooperating with companies (BMMT, TaUYou and UniversalDoctor) as a consultant.