Unsupervised Semantic Parsing

Hoifung Poon and Pedro Domingos

Abstract:

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 them to 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 knowledge base from biomedical abstracts and answer questions. USP substantially outperforms TextRunner, DIRT and an informed baseline on both precision and recall on this task.

Download:

Paper (PDF)
USP code (released under the Modified BSD License.)
User guide

Datasets used:

Questions
Answers extracted by USP (with manual labels)
GENIA