Learning an Executable Neural Semantic Parser
This work addresses the challenge of creating executable semantic parsers for tasks like querying knowledge bases or databases, representing an incremental improvement by combining existing techniques in a novel way.
The paper tackles the problem of mapping natural language to executable logical forms by introducing a neural semantic parser that uses a transition-based approach with structured recurrent neural networks and attention mechanisms. Experiments across multiple datasets demonstrate its effectiveness in various training settings, including supervised, weakly-supervised, and distant supervision.
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser generates tree-structured logical forms with a transition-based approach which combines a generic tree-generation algorithm with domain-general operations defined by the logical language. The generation process is modeled by structured recurrent neural networks, which provide a rich encoding of the sentential context and generation history for making predictions. To tackle mismatches between natural language and logical form tokens, various attention mechanisms are explored. Finally, we consider different training settings for the neural semantic parser, including a fully supervised training where annotated logical forms are given, weakly-supervised training where denotations are provided, and distant supervision where only unlabeled sentences and a knowledge base are available. Experiments across a wide range of datasets demonstrate the effectiveness of our parser.