Log In Sign Up

From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction

by   Robert Vacareanu, et al.

While deep learning approaches to information extraction have had many successes, they can be difficult to augment or maintain as needs shift. Rule-based methods, on the other hand, can be more easily modified. However, crafting rules requires expertise in linguistics and the domain of interest, making it infeasible for most users. Here we attempt to combine the advantages of these two directions while mitigating their drawbacks. We adapt recent advances from the adjacent field of program synthesis to information extraction, synthesizing rules from provided examples. We use a transformer-based architecture to guide an enumerative search, and show that this reduces the number of steps that need to be explored before a rule is found. Further, we show that without training the synthesis algorithm on the specific domain, our synthesized rules achieve state-of-the-art performance on the 1-shot scenario of a task that focuses on few-shot learning for relation classification, and competitive performance in the 5-shot scenario.


Learning Compositional Rules via Neural Program Synthesis

Many aspects of human reasoning, including language, require learning ru...

Example-based Synthesis of Static Analysis Rules

Static Analysis tools have rules for several code quality issues and the...

Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems

Dialogue policy optimisation via reinforcement learning requires a large...

PBRE: A Rule Extraction Method from Trained Neural Networks Designed for Smart Home Services

Designing smart home services is a complex task when multiple services w...

Matching Networks for One Shot Learning

Learning from a few examples remains a key challenge in machine learning...

Ensemble Making Few-Shot Learning Stronger

Few-shot learning has been proposed and rapidly emerging as a viable mea...

PLANS: Robust Program Learning from Neurally Inferred Specifications

Recent years have seen the rise of statistical program learning based on...