A Deep Architecture for Semantic Parsing
This addresses the problem of semantic parsing for noisy or low-resource language data, though it appears incremental as it builds on neural models.
The paper tackles semantic parsing by introducing a deep learning architecture that generates ontology-specific queries from natural language without parsing, making it suitable for malformed text like tweets and resource-poor languages.
Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries. This paper presents a novel deep learning architecture which provides a semantic parsing system through the union of two neural models of language semantics. It allows for the generation of ontology-specific queries from natural language statements and questions without the need for parsing, which makes it especially suitable to grammatically malformed or syntactically atypical text, such as tweets, as well as permitting the development of semantic parsers for resource-poor languages.