SLFNet: Generating Semantic Logic Forms from Natural Language Using Semantic Probability Graphs
This addresses a specific bottleneck in natural language interfaces for semantic parsing, offering an incremental improvement over existing methods.
The paper tackles the problem of 'order matters' in sequence-to-sequence models for generating semantic logic forms from natural language by proposing SLFNet, which incorporates syntactic information and semantic probability graphs, achieving state-of-the-art performance on ChineseQCI-TS and Okapi datasets and competitive results on ATIS.
Building natural language interfaces typically uses a semantic parser to parse the user's natural language and convert it into structured \textbf{S}emantic \textbf{L}ogic \textbf{F}orms (SLFs). The mainstream approach is to adopt a sequence-to-sequence framework, which requires that natural language commands and SLFs must be represented serially. Since a single natural language may have multiple SLFs or multiple natural language commands may have the same SLF, training a sequence-to-sequence model is sensitive to the choice among them, a phenomenon recorded as "order matters". To solve this problem, we propose a novel neural network, SLFNet, which firstly incorporates dependent syntactic information as prior knowledge and can capture the long-range interactions between contextual information and words. Secondly construct semantic probability graphs to obtain local dependencies between predictor variables. Finally we propose the Multi-Head SLF Attention mechanism to synthesize SLFs from natural language commands based on Sequence-to-Slots. Experiments show that SLFNet achieves state-of-the-art performance on the ChineseQCI-TS and Okapi datasets, and competitive performance on the ATIS dataset.