Context Dependent Semantic Parsing: A Survey
It provides a comprehensive overview for researchers working on improving semantic parsing by incorporating context, but is incremental as it surveys existing work rather than introducing new methods.
This survey examines context dependent semantic parsing, which addresses the inability of most current methods to use contextual information like dialogue history, and reviews progress in methods, datasets, and tasks while identifying open challenges.
Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations. Currently, most semantic parsing methods are not able to utilize contextual information (e.g. dialogue and comments history), which has a great potential to boost semantic parsing performance. To address this issue, context dependent semantic parsing has recently drawn a lot of attention. In this survey, we investigate progress on the methods for the context dependent semantic parsing, together with the current datasets and tasks. We then point out open problems and challenges for future research in this area. The collected resources for this topic are available at:https://github.com/zhuang-li/Contextual-Semantic-Parsing-Paper-List.