Freebase QA: Information Extraction or Semantic Parsing?
Xuchen Yao, Jonathan Berant, Benjamin Van Durme · 2014
We contrast two seemingly distinct ap-proaches to the task of question answering (QA) using Freebase: one based on infor-mation extraction techniques, the other on semantic parsing. Results over the same test-set were collected from two state-of-the-art, open-source systems, then ana-lyzed in consultation with those systems’ creators. We conclude that the differ-ences between these technologies, both in task performance, and in how they get there, is not significant. This sug-gests that the semantic parsing commu-nity should target answering more com-positional open-domain questions that are beyond the reach of more direct informa-tion extraction methods.