The 30th UW/MS Symposium in Computational Linguistics
Microsoft Research and University of Washington
Time: 3:30-5PM, Fri 5/17/2013
Location: Paccar Hall, Room 291, University of Washington
Come take advantage of this opportunity to connect with the computational linguistics community at Microsoft and the University of Washington. This is a regular opportunity for computational linguists at the University of Washington and at Microsoft to discuss topics in the field and to connect in a friendly informal atmosphere. We will have two talks (see below), followed by informal mingling.
We present the first unsupervised approach for semantic parsing that rivals the accuracy of supervised approaches in translating natural-language questions to database queries. Our GUSP system produces a semantic parse by annotating the dependency-tree nodes and edges with latent states, and learns a probabilistic grammar using EM. To compensate for the lack of example annotations or question-answer pairs, GUSP adopts a novel grounded-learning approach to leverage the database content for indirect supervision. On the challenging ATIS dataset, GUSP attained an accuracy of 84%, effectively tying with the best published results by supervised approaches.
Hoifung Poon is a researcher at Microsoft Research. His research interests is in advancing machine learning and natural language processing for automating discovery in genomics and precision medicine. His most recent work focuses on scaling semantic parsing to extract biological pathways from Pubmed, and on developing probabilistic methods to incorporate pathways with high-throughput genomics data in cancer system biology. He has received Best Paper Awards in NAACL, EMNLP, and UAI.
The development of knowledge base creation systems has mainly focused on information extraction without considering how to effectively reason over their databases of facts. One reason for this is that the inference required to learn a probabilistic knowledge base from text at any realistic scale is intractable. In this paper, we propose formulating the joint problem of fact extraction and probabilistic model learning in terms of Tractable Markov Logic (TML), a subset of Markov logic in which inference is low-order polynomial in the size of the knowledge base. Using TML, we can tractably extract new information from text while simultaneously learning a probabilistic knowledge base. We will also describe a testbed for our proposal: creating a biomedical knowledge base and making it available for querying on the Web.
(This is joint work with Pedro Domingos.)
Chloé Kiddon is a fifth year graduate student at the University of Washington in Computer Science & Engineering. She works on machine learning, natural language understanding, and knowledge base construction. She received her B.S. with honors in Computer Science from Stanford University in 2008. She has been an NSF Graduate Fellow since 2010.
Reception will follow in the same location
The University of Washington is committed to providing access, equal opportunity, and reasonable accommodations in its services, programs, activities, education, and employment for individuals with disabilities.
To request disability accommodations, please contact the Office of the ADA Coordinator in advance.
545-6450 (voice); 543-6452 (TDD); firstname.lastname@example.org (e-mail).