Unsupervised Semantic Parsing

We present the first unsupervised approach to the problem of learning a semantic parser, using Markov logic. Our USP system transforms dependency trees into quasi-logical forms, recursively induces lambda forms from these, and clusters abstract away syntactic variations of the same meaning. The MAP semantic parse of a sentence is obtained by recursively assigning its parts to lambda-form clusters and composing them. We evaluate our approach by using it to extract a e base from biomedical abstracts and answer questions. USP substantially outperforms TextRunner, DIRT and an informed baseline on both precision and recall on this task.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Hoifung Poon, Pedro Domingos
• Keywords: EMNLP 2009, MAP Semantic Parse, Natural Language Processing, Semantic Parser, Unsupervised Approach