Seminar talk titled “Entities with Quantities: Extraction, Search, and Ranking”
Title Of the Talk: Entities with Quantities: Extraction, Search, and Ranking
Speaker: Koninika Pal
Date &Time: Wednesday, 08th Jan 2020 14:30
Venue: Room No A220
Quantities are more than mere numbers. They represent measures for entities, expressed in numbers with associated units, and appear in search queries in numerous forms: companies with annual revenue of at least 50 Mio USD, athletes who ran 200 meters faster than 19.5 s, electric cars with range above 400 miles, and so on. Processing such queries requires understanding the quantities, where capturing the surrounding context is an essential part of it. Modern search engines and QA systems have gone a long way towards understanding entities and their type, but they consider numbers and units as simple keywords. Therefore they often fail on properly interpreting quantities in queries and generating the candidate answers when the specifics of the search condition (less than, above, etc.), the units of interest (seconds, miles, meters, etc.) and the context of the quantity matter (annual or quarterly revenue, etc.).
Koninika Pal is a postdoctoral researcher in the department of Databases and Information Systems at Max Planck Institute for Informatics, Saarbruecken, Germany. She received her PhD from Technical University Kaiserslautern, Germany in 2018. Her dissertation focused on building smart indexing methods for efficient querying of ranked lists and mining interesting categories for exploring ranked entities. She did her masters’ at NIT Durgapur in 2012 and her bachelors at West Bengal University of Technology in 2009 in Computer Science and Engineering. After her masters’, she worked as a research assistant at IIT Kharagpur in 2012. Her research interests broadly cover the area of information extraction and knowledge base curation. Currently, she is working on extracting and canonicalizing commonsense assertions, harvesting peer entities, and building a QA system to handle quantitative queries. More details are available at http://people.mpi-inf.mpg.de/~kpal/
Wednesday, 08th Jan 2020 14:30