Adaptation of Machine Translation to Specific Domains and Applications

Speaker:
Pavel Pecina
Abstract:
Domain adaptation of machine translation deals with the problem when the domain of training data of a machine translation system differs from its target domain. In our work, not only we address adaptation to specific domains (e.g. medical), but also genres (search queries), and applications (cross-lingual information retrieval). The talk reviews our current and previous work in this area which has been conducted within three EU projects: Panacea, Khresmoi, and KConnect and reports the main findings and results.
Length:
01:20:10
Date:
14/11/2016
views:

Images:
Attachments: (video, slides, etc.)
111 MB
20 downloads
923 MB
22 downloads
130 MB
21 downloads
185 MB
21 downloads
390 MB
21 downloads