Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
arXiv:2101.01686
Abstract
Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. Central to the problem is the challenge of leveraging contextual information of both natural language utterance and database schemas in the interaction history. In this paper, we present a dynamic graph framework that is capable of effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds. The framework employs a dynamic memory decay mechanism that incorporates inductive bias to integrate enriched contextual relation representation, which is further enhanced with a powerful reranking model. At the time of writing, we demonstrate that the proposed framework outperforms all existing models by large margins, achieving new state-of-the-art performance on two large-scale benchmarks, the SParC and CoSQL datasets. Specifically, the model attains a 55.8% question-match and 30.8% interaction-match accuracy on SParC, and a 46.8% question-match and 17.0% interaction-match accuracy on CoSQL.
Accepted by AAAI 2021
References in corpus (9)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- The Natural Language Decathlon: Multitask Learning as Question Answering
- A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
- FlowQA: Grasping Flow in History for Conversational Machine Comprehension
- Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
- SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task