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

arXiv: https://arxiv.org/abs/2403.19936 · HTML: https://mlsanity.com/paper/2403.19936/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning](https://mlsanity.com/paper/2105.14517/) (2021)
- [Incorporating Copying Mechanism in Sequence-to-Sequence Learning](https://mlsanity.com/paper/1603.06393/) (2016)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Conversational Semantic Parsing](https://mlsanity.com/paper/2009.13655/) (2020)
- [Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum](https://mlsanity.com/paper/2312.06441/) (2023)
- [Learning Structured Natural Language Representations for Semantic Parsing](https://mlsanity.com/paper/1704.08387/) (2017)
- [Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts](https://mlsanity.com/paper/2402.05970/) (2024)
- [Compositional Generalization for Natural Language Interfaces to Web APIs](https://mlsanity.com/paper/2112.05209/) (2021)
- [DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting](https://mlsanity.com/paper/2403.02914/) (2024)
- [A Practical Chinese Dependency Parser Based on A Large-scale Dataset](https://mlsanity.com/paper/2009.00901/) (2020)
- [Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection](https://mlsanity.com/paper/2311.10370/) (2023)
- [Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance](https://mlsanity.com/paper/2403.13850/) (2024)
- [Exploring Global and Local Information for Anomaly Detection with Normal Samples](https://mlsanity.com/paper/2306.02025/) (2023)

## Built on by (most cited first, 1 of 1)

- [GLADformer: A Mixed Perspective for Graph-level Anomaly Detection](https://mlsanity.com/paper/2406.00734/) (2024)

## Abstract (arXiv)

Building natural language interfaces typically uses a semantic parser to parse the user's natural language and convert it into structured Semantic Logic Forms (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.