|  |
演讲简介
Most work on event extraction frames the problem as classification at some level, addressing it with supervised machine learning. All such approaches model individual types and their corresponding expressions in isolation, failing to exploit coordination and correlation among types. They routinely fail to exploit linguistic expressions that express none of the prescribed types. The shift to deep learning has led to improvements in extraction quality, but the greater data needs of these methods has only exacerbated the overhead of adding new types, and their most sensitive models are highly domain-specific. The field’s substantial investment in semi-supervised methods, such as distant supervision, has reduced development overheads considerably, but the application of these techniques is limited to types known in advance. In contrast, we provide a new angle on event extraction, modeling it as a generic grounding task by taking advantage of structures latent in the type system via a novel zero-shot transfer learning framework. In this new paradigm, linguistic expressions in multiple sources are grounded into an infinitely extensible and rapidly adaptable continuous space of types. In addition, we will systematically overview recent efforts at improving the quality and portability of event extraction, and discuss remaining challenges and potential solutions together with the audience by looking into many error examples.
关于讲者
Heng Ji is the Edward P. Hamilton Chair Professor in Computer Science at Rensselaer Polytechnic Institute. She received her Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Information Extraction and Knowledge Base Population. She was selected as "Young Scientist" and a member of the Global Future Council on the Future of Computing by the World Economic Forum in 2016, 2017 and 2018. She received "AI's 10 to Watch" Award by IEEE Intelligent Systems in 2013, NSF CAREER award in 2009, Google Research Awards in 2009 and 2014, IBM Watson Faculty Award in 2012 and 2014, and Bosch Research Awards in 2015, 2016 and 2017. She coordinated the NIST TAC Knowledge Base Population task since 2010, and led various government sponsored research projects, including the DARPA DEFT TinkerBell team and the ARL NS-CTA Knowledg Networks Construction task. She has served as a panelist for US Air Force 2030, and the Program Committee Co-Chair of several conferences including NAACL-HLT2018.
