Advanced Lecture Series in Pattern Recognition
题 目 (TITLE)：Language Understanding cum Knowledge Yield
讲 座 人 (SPEAKER)：Dr. Feiyu Xu and Prof. Hans Uszkoreit(DFKI )
时 间 (TIME)：10:15 am, November 23 (Wednesday), 2016
主 持 人 (CHAIR)：Prof. Chengqing Zong
地 点 (VENUE)：No.1 Conference Room (3rd floor), Intelligence Building
Understanding natural language is at the core of helping people get the information they need as quickly and easily as possible. Recent research and development have created the necessary ingredients for a major push in web-scale language understanding: large repositories of structured knowledge, progress in language processing, linguistic knowledge resources and new powerful techniques for machine learning. In this talk, we will report our research results in the area of relation extraction, in particular results achieved in our Google Focused Research Award Project LUcKY. We developed a machine learning platform which can employ huge collections of known facts and millions of web pages mentioning these facts for learning the linguistic patterns people use to express such facts. With the help of the learned patterns, new facts are discovered in digital texts such as in the media or reports. We have built an open source called Sar-graphs (sargraph.dfki.de), a new kind of linguistic knowledge resource containing dependency pattern networks for 25 real world relations. Sar-graphs have also been automatically linked to WordNet, BabelNet and FrameNet, contributing to linked linguistic open data (LLOD). Furthermore, we will report our work on entity linking and cross-sentence event linking. Our work on sar-graphs, entity linking and event linking has been published at ACL 2015, Journal of Web Semantics 2 (special issue on Knowledge Graphs 2016) and CoNLL 2016.
Bio of Hans:
Professor Dr. Hans Uszkoreit is Scientific Director at the German Research Center for Artificial Intelligence (DFKI) and Head of the DFKI Language Technology Lab, also site coordinator of DFKI Berlin. He is head of the Language Technology Division at DFKI. His lab has performed research in information extraction, crosslingual IR, question answering, parsing, machine translation and deep linguistic processing. Uszkoreit’s research is documented in more than 200 international publications. He received his Ph.D. in 1984 from the University of Texas at Austin and then held research positions at Stanford University, SRI International and IBM Germany. From 1988-2015 he also worked as Professor for Computational Linguistics and (coopted) for Computer Science at Saarland University in Saarbruecken. Since 2002, Prof. Uszkoreit is Member of the European Academy of Sciences. He is also a Permanent Member of the International Committee of Computational Linguistics (ICCL), Honorary Professor at Technische Universität Berlin and Past President of the European Association for Logic, Language and Information and he serves on several international editorial and advisory boards.
Bio of Feiyu :
Dr. Feiyu Xu is Principal Researcher and Head of Research Group Text Analytics in the Language Technology Lab of DFKI. Feiyu Xu studied technical translation at Tongji University in Shanghai from 1987 to 1990. She then studied computational linguistics at Saarland University from 1992 to 1998 and graduated by receiving a Diplom (MSc) with distinction. Her PhD-Thesis is about "bootstrapping relation extraction from semantic seed" in "information extraction". In 2014, Feiyu Xu has completed a habilitation in big text data analytics. In 2012, Feiyu Xu has won a Google Focused Research Award for Natural Language Understanding as co-PI with Hans Uszkoreit and Roberto Navigli. In 2014, Feiyu Xu was honored as DFKI Research Fellow. Her research is documented in more than 90 publications including conference papers for ACL, COLING, EMNLP, CONLL, NAACL, LREC etc. She is area chair of EACL 2017 for text mining, information extraction and question answering.