Scaling Semantic Parsers with On-the-Fly Ontology Matching
Citations Over TimeTop 1% of 2013 papers
Abstract
We consider the challenge of learning semantic parsers that scale to large, open-domain problems, such as question answering with Freebase.In such settings, the sentences cover a wide variety of topics and include many phrases whose meaning is difficult to represent in a fixed target ontology.For example, even simple phrases such as 'daughter' and 'number of people living in' cannot be directly represented in Freebase, whose ontology instead encodes facts about gender, parenthood, and population.In this paper, we introduce a new semantic parsing approach that learns to resolve such ontological mismatches.The parser is learned from question-answer pairs, uses a probabilistic CCG to build linguistically motivated logicalform meaning representations, and includes an ontology matching model that adapts the output logical forms for each target ontology.Experiments demonstrate state-of-the-art performance on two benchmark semantic parsing datasets, including a nine point accuracy improvement on a recent Freebase QA corpus.
Related Papers
- → A Framework for Ontology Evaluation(2010)38 cited
- → Towards a Multi-level Upper Ontology/ foundation Ontology Framework as Background Knowledge for Ontology Matching Problem(2015)6 cited
- Grounding the Foundations of Ontology Mapping on the Neglected Interoperability Ambition.(2008)
- → Methodology(2013)
- → Meta Model(2009)