Object-oriented Neural Programming (OONP) for Document Understanding

TL;DR

OONP is a neural framework that semantically parses domain-specific documents into object-oriented structures, supporting various training methods and handling complex ontologies with limited data.

Contribution

Introduces OONP, a novel neural-based framework for semantic document parsing into domain-specific object-oriented ontologies, adaptable with multiple training strategies.

Findings

Effective on synthetic and real-world tasks

Handles complex ontologies with modest data

Supports diverse training methods

Abstract

We propose Object-oriented Neural Programming (OONP), a framework for semantically parsing documents in specific domains. Basically, OONP reads a document and parses it into a predesigned object-oriented data structure (referred to as ontology in this paper) that reflects the domain-specific semantics of the document. An OONP parser models semantic parsing as a decision process: a neural net-based Reader sequentially goes through the document, and during the process it builds and updates an intermediate ontology to summarize its partial understanding of the text it covers. OONP supports a rich family of operations (both symbolic and differentiable) for composing the ontology, and a big variety of forms (both symbolic and differentiable) for representing the state and the document. An OONP parser can be trained with supervision of different forms and strength, including supervised learning (SL) , reinforcement learning (RL) and hybrid of the two. Our experiments on both synthetic and real-world document parsing tasks have shown that OONP can learn to handle fairly complicated ontology with training data of modest sizes.