SLFNet: Generating Semantic Logic Forms from Natural Language Using Semantic Probability Graphs

TL;DR

SLFNet is a novel neural network that improves semantic parsing by incorporating syntactic dependencies and semantic probability graphs, enabling more accurate conversion of natural language to semantic logic forms.

Contribution

The paper introduces SLFNet, which combines syntactic prior knowledge and semantic probability graphs with a Multi-Head SLF Attention mechanism for better semantic parsing.

Findings

Achieves state-of-the-art results on ChineseQCI-TS and Okapi datasets.

Demonstrates competitive performance on the ATIS dataset.

Effectively captures long-range dependencies in natural language commands.

Abstract

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.