Developing a Concept-Oriented Search Engine for Isabelle Based on Natural Language : Technical Challenges

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

• Yiannos Stathopoulos and Angeliki Koutsoukou-Argyraki
• Tuesday 02 June 2020, 13:15-14:15
• Online on Teams.

If you have a question about this talk, please contact Mateja Jamnik.

ONLINE link

We introduce SErAPIS (: Search Engine by the Alexandria Project for ISabelle), a work-in-progress search engine for the Isabelle libraries. SErAPIS uses an offline index (all libraries are indexed a-priori) that enables library search using natural language and does not rely on the loaded libraries. We describe the SErAPIS pipeline that indexes Isabelle facts by associating them to words and concepts (special phrases that refer to mathematical structures, objects and ideas) in Wikipedia mathematics articles. We also describe three models for extracting textual descriptions of facts from these articles and present a preliminary experiment with four retrieval models based on our indexing methods. We are planning several further developments to the engine as well as an extensive evaluation using online user data.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• Online on Teams
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list

Note that ex-directory lists are not shown.