University of Cambridge > Talks.cam > Language Technology Lab Seminars > Senses can help vector space models of lexical substitution

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹī¸ Information

Senses can help vector space models of lexical substitution

Download to your calendar using vCal

If you have a question about this talk, please contact Dimitri Kartsaklis .

The role of senses in NLP applications has been questioned due to the high performance of vector space models in semantic tasks. These models deliver state-of-the-art performance without explicitly accounting for senses which have even been shown to be harmful for some tasks. In this talk, I will show how sense representations tailored to the task can improve the results of vector-based lexical substitution models. I will discuss two aspects related to paraphrase substitution, namely their clusterability into senses and their substitutability in context. Finally, I will present preliminary results on core sense detection through a multi-view approach to paraphrase semantic analysis.

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

Average on Saturdays: 7615.73809524 kWh BAS Seminar Room 1; https://bas-ac-uk.zoom.us/j/92407581181 Downing College, Regent Street, Cambridge

Other talks

How Much Does Homology Really Know? Feedback and the circumgalactic medium Morning Break Title to be confirmed An Amphibious Urbanism | | Cut 4: The Desert Arrives Slowly Talk TBC
 

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