Large-scale Semantic Parsing without Question-Answer Pairs

Querying a database to retrieve an answer, telling a robot to perform
an action, or teaching a computer to play a game are tasks requiring
communication with machines in a language interpretable by
them. Semantic parsing addresses the specific task of learning to map
natural language to machine interpretable formal meaning
representations. Traditionally, sentences are converted into logical
form grounded in the symbols of some fixed ontology or relational
database. Approaches for learning semantic parsers have been for the
most part supervised, using manually annotated training data
consisting of sentences and their corresponding logical forms. More
recently, methods which learn from question-answer pairs have been
gaining momentum as a means of scaling semantic parsers to large,
open-domain problems.

In this talk, I will present an approach to semantic parsing that does
not require example annotations or question-answer pairs but instead
learns from a large knowledge base and web-scale corpora. Our semantic
parser exploits Freebase, a large community-authored knowledge base
that spans many sub-domains and stores real world facts in graphical
format, and parsed sentences from a large corpus. Our key insight is
to represent natural language via semantic graphs whose topology
shares many commonalities with Freebase. Given this representation, we
conceptualize semantic parsing as a graph matching problem.  We
convert the output of an open-domain combinatory categorial grammar
(CCG) parser into a graphical representation and subsequently map it
onto Freebase, guided by denotations as a form of weak
supervision. Evaluation experiments on two benchmark datasets show
that our semantic parser improves over state-of-the-art approaches.