Composing Information, Extraction, Semantic Parsing and Tractable Inference for Deep NLP
Abstract
We developed new information extraction technologies. Our Vinculum entity linker is simple and modular; we compare it to other top systems analyze approaches to mention extraction, candidate generation, entity type prediction, entity coreference,and coherence. We also developed both unsupervised and semi-supervised algorithms for event extraction that exploit parallel news streams, showing significant performance improvements on multiple event extractors over ACE2005 and TAC-KBP 2015 datasets. Finally, we developed new natural language processing tools (e.g., semantic parsing) and introduced efficient inference algorithms for extracted knowledge bases.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 24, 2018
- Accession Number
- AD1052274
Entities
People
- Daniel S. Weld
- Hannaneh Hajishirzi
- Luke Zettlemoyer
- Pedro Domingos
Organizations
- University of Washington