BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RDATE:20261025T030000
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.30781.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260502T124817Z
CREATED:20260429T080547Z
DESCRIPTION:Abstract:The harmful impact of disinformation on society and in
 dividuals is large and growing. Reliable knowledge about the world\, and a
 bout our information space\,can be leveraged to diminish this negative imp
 act. I will present research carried in my team to leverage high-quality r
 eference information. In the StatCheck project\, transferred to RadioFranc
 e\, we focus on making high-quality statistics available and easy to searc
 h. We show that naive use of LLMs is not only expensive\, it also fails to
  handle information searches in very large statistic corpora.Instead\, we 
 present a frugal and higher-quality approach\, that follows the specific n
 ature of statistic datasets to better answer user queries over such corpor
 a. Then\, I will present an efficient approach\, based on reinforcement le
 arning\, which identifies within a given Web site all the files having cer
 tain user-specified types. This allows in particular to find all statistic
  files within varied-structure web sites\, to be used as a basis for fact-
 checking.Joint work with Oana Balalau\, Helena Galhardas (INESC-ID Portuga
 l)\, Antoine Gauquier and Pierre Senellart (ENS and Inria)\, and other col
 leagues.Bio sketch:Ioana Manolescu is a senior researcher at Inria\, in Fr
 ance. She is the lead of the CEDAR INRIA team focusing on rich data analyt
 ics at cloud scale. She is also the president of BDA\, the French national
  scientific association focused on data management. She is or has been a m
 ember of the PVLDB Endowment Board of Trustees\, of the ACM SIGMOD Executi
 ve Committee\, as well as program chair\, general chair\, and editorial ro
 les in major conferences and journals on data management and the Web. She 
 is a Senior ACM member and a recipient of the ACM SIGMOD 2020 Contribution
  Award.Ioana has co-authored more than 200 articles in international journ
 als and conferences and several books. Her main research interests encompa
 ss blending Data and AI methods for working with complex\, semistructured 
 data\, in particular for large heterogeneous text-and-data graphs. In the 
 last decade\, her research has tackled several problems raised by journali
 stic fact-checking and investigative journalism\, an area where she has co
 llaborated successfully with journalists from Le Monde and RadioFrance. 
DTSTART;TZID=Europe/Paris:20260508T153000
DTEND;TZID=Europe/Paris:20260508T153000
LAST-MODIFIED:20260429T081108Z
LOCATION:Aula Magna del DIAG
SUMMARY:Knowledge is Power: Fighting Disinformation with Data and AI - Prof
 . Ioana Manolescu
URL;TYPE=URI:https://www.diag.uniroma1.it/node/30781
END:VEVENT
END:VCALENDAR
