University of Cambridge > Talks.cam > Language Technology Lab Seminars > Natural Language Processing to Bridge Heterogeneous Data

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Natural Language Processing to Bridge Heterogeneous Data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Mohammad Taher Pilehvar.

Natural language is a primary means to communicate information, while our daily life also relies on other types of media such as vision and numerical data. I will talk about our recent efforts on developing methods for accessing non-text data via natural language. Specifically, i) semantic parsing for querying structured databases, ii) text generation for videos and time-series data, and iii) semantic representations for visual information, are introduced.

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

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Type the title of a new list here Stroke Research Meetings Pragmatics reading group 2012-13

Other talks

Environmental shocks and demographic consequences in England: 1280-1325 and 1580-1640 compared Poison trials, panaceas and proof: debates about testing and testimony in early modern European medicine Superconformal quantum mechanics and integrability Assessment of data completeness in the National Cancer Registry and the impact on the production of Cancer Survival Statistics Autumn Cactus & Succulent Show
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity