For best experience please turn on javascript and use a modern browser!
You are using a browser that is no longer supported by Microsoft. Please upgrade your browser. The site may not present itself correctly if you continue browsing.

Training statistical machine translation systems on heterogenous corpora can result in suboptimal performance. Cuòng Hoang shows that domain-confused statistics may harm the performance of both word alignment and phrase-based models.

Event details of Domain models for statistical machine translation
Date 5 July 2017
Time 16:00 -17:00
Location Agnietenkapel
Room Location

C. Hoàng: Latent Domain Models for Statistical Machine Translation.

Supervisor

Prof. K. Sima'an

Co-supervisor

Dr I.A. Titov

Agnietenkapel

Room Location

Oudezijds Voorburgwal 229 - 231
1012 EZ Amsterdam

Entrance

This event is open to the public.