[ Time: 6pm CET, 7pm GMT+3 ]
Businesses requesting translations like to see consistency in the tone and terminology used. However, when many different translators work to translate documents for the business, it is difficult to ensure that translations remain consistent over time.
While the use of NMT can improve translation speed for businesses, fixing inconsistent terminology represents a significant portion of the post-editing effort for translators.
A robust NMT system should be able to incorporate term translations from human-curated term banks as guidance, to ensure more consistent translations from the start.
In this talk, we are going to present:
- How term banks are used in the typical translation industry workflow
- Challenges and methods for identifying terms from the term bank in the source sentence
- Methods for incorporating term guidance in the NMT system, agnostic to the specific term bank used at inference time
[ Image source - "Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation" (Post, Matt and Vilar, David, 2018) ]
Svetlana Tchistiakova, an Applied Scientist in MT at lengoo, will discuss lengoo’s approach.
The full link to join will be published 15min before the meetup.
Как нас найти:
Организатор: Natural Language Processing group Belarus
Official group of Natural Language Processing and Computational Linguistics in Belarus [http://nlproc.by/] The group for those who are interested in computational linguistics and natural language processing (NLProc).
“Human knowledge is expressed in language. So computational linguistics is very important.”–Mark Steedman, ACL Presidential Address (2007)