University of Cambridge > Talks.cam > NLIP Seminar Series > Stream-based Statistical Machine Translation

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Stream-based Statistical Machine Translation

Download to your calendar using vCal

If you have a question about this talk, please contact Ekaterina Kochmar .

We investigate a new approach for SMT system training within the streaming model of computation. We develop and test incrementally retrainable models which, given an incoming stream of new data, can efficiently incorporate the stream data online. A naive approach using a stream would use an unbounded amount of space. Instead, our online SMT system can incorporate information from unbounded incoming streams and maintain constant space and time. Crucially, we are able to match (or even exceed) translation performance of comparable systems which are batch retrained and use unbounded space. Our approach is particularly suited for situations when there is arbitrarily large amounts of new training material and we wish to incorporate it efficiently and in small space. Our stream-based SMT system is efficient for tackling massive volumes of new training data and offers-up new ways of thinking about translating web data and dealing with other natural language streams.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8928.62547893 kWh LfL Lunchtime Seminar - Case Study and Strengths Approaches Research Live on Zoom, pre-registration essential here using link circulated by email

Other talks

Title TBC Gastroenterology and Acute Medicine Differences between Robin and Neumann eigenvalues Title to be confirmed Group Work Cultural evolution creates language-like structure: from humans to humpback whales and beyond
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity