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
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.29372.field_data.0@www.ugov-ricerca.uniroma1.it
DTSTAMP:20260404T223316Z
CREATED:20250609T075136Z
DESCRIPTION:Abstract  Language Models have brought major breakthroughs in n
 atural language processing. Notwithstanding this success\, I will show tha
 t certain applications still need symbolic representations. I will then sh
 ow how different methods (language models and others) can be harnessed to 
 build such symbolic representations in the form of knowledge bases. I will
  highlight several challenges in this endeavor\, from finding good embeddi
 ngs to improving entity linking and dealing with fallacies and textual ent
 ailment. I will also discuss how language models can be evaluated along se
 veral dimensions. Finally\, I will talk about the knowledge bases themselv
 es\, most notably our YAGO project. I will present our work on detecting a
 nd alleviating incompleteness in knowledge bases\, on querying the data\, 
 on using the data for the digital humanities\, and on reasoning on beliefs
 . BioFabian M. Suchanek is a full professor at the Intitut Polytechnique d
 e Paris in France. He obtained his doctorate at the Max-Planck Institute f
 or Computer Science in Germany. In his thesis\, Fabian developed the YAGO 
 knowledge base\, one of the largest public knowledge bases\, which earned 
 him an honorable mention of the SIGMOD thesis prize\, as well as\, 10 year
 s later\, the “Test of Time” of The Web Conference 2018. Fabian was a post
 doctoral fellow at Microsoft Research in Silicon Valley and at INRIA Sacla
 y. Then he led a research group at the Max-Planck Institute for Computer S
 cience. In 2013\, he became an associate professor\, and in 2016 a full pr
 ofessor at Télécom Paris\, now part of Intitut Polytechnique de Paris. Wit
 h his students\, Fabian works on natural language processing\, neuro-symbo
 lic reasoning\, information extraction\, rule mining\, and knowledge graph
  management. He has published over 100 scientific papers\, and his work ha
 s been cited over 19\,000 times.  
DTSTART;TZID=Europe/Paris:20250625T140000
DTEND;TZID=Europe/Paris:20250625T150000
LAST-MODIFIED:20250609T082734Z
LOCATION:Aula A2 del DIAG
SUMMARY:On Language Models and Knowledge Bases - Prof. Fabian M. Suchanek
URL;TYPE=URI:http://www.ugov-ricerca.uniroma1.it/node/29372
END:VEVENT
END:VCALENDAR