University of Cambridge > Talks.cam > Language Technology Lab Seminars > Unsupervised Domain Adaptation for Neural Search

  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

Unsupervised Domain Adaptation for Neural Search

Download to your calendar using vCal

If you have a question about this talk, please contact Marinela Parovic .

After textual information retrieval has stalled for many years, pre-trained transformer networks gave a big performance boost resulting in extremely better search results. However, so far these approaches require large amount of training data which is seldom available for many use-cases. In this talk, I will start with an overview of different neural search approach. I will then present BEIR , a benchmark that test neural search methods in an out-of-domain setting. As the benchmark reveals, many architecture are sensitive to domain shifts limiting their usefulness for many real word applications. To overcome this short-coming, we created Generative Pseudo Labeling (GPL), a method that transfers knowledge from slow, but robust architectures, to fast but domain-sensitive approaches, which results in highly improved search quality.

This talk is part of the Language Technology Lab Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Webinar & FW11, Computer Laboratory, William Gates Building. Type the title of a new list here German Society Speaker Events

Other talks

The elephant in the room: Machine Learning directly into physical models Together Now: Cooperation and Collaboration in Social Art Practice Paediatric Medicine and Rheumatology Emergency Medicine and Metabolic Medicine Afternoon Break Precarity and the economy of makeshifts: A novel argument from the census of England, 1851-1911
 

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