Joint Extraction of Multiple Relations and Entities from Building Code Clauses

Fulin Li,Yuanbin Song,Yongwei Shan

doi:10.3390/app10207103

Fulin Li, Yuanbin Song + Show 1 more

Open Access

https://doi.org/10.3390/app10207103

Copy DOI

Abstract

The extraction of regulatory information is a prerequisite for automated code compliance checking. Although a number of machine learning models have been explored for extracting computer-understandable engineering constraints from code clauses written in natural language, most are inadequate to address the complexity of the semantic relations between named entities. In particular, the existence of two or more overlapping relations involving the same entity greatly exacerbates the difficulty of information extraction. In this paper, a joint extraction model is proposed to extract the relations among entities in the form of triplets. In the proposed model, a hybrid deep learning algorithm combined with a decomposition strategy is applied. First, all candidate subject entities are identified, and then, the associated object entities and predicate relations are simultaneously detected. In this way, multiple relations, especially overlapping relations, can be extracted. Furthermore, nonrelated pairs are excluded through the judicious recognition of subject entities. Moreover, a collection of domain-specific entity and relation types is investigated for model implementation. The experimental results indicate that the proposed model is promising for extracting multiple relations and entities from building codes.

Highlights

Automated code compliance checking is a promising alternative to manual checking that is expected to reduce time consumption, cost, and errors [1]
A typical case is to automatically review the area of a kitchen in a residential building, where the code requirement “The area of a kitchen shall not be less than 4 m2 ” should be satisfied. Such an engineering constraint is hard-coded by software engineers into e-PlanCheck while the area of the kitchen is automatically calculated from a digital drawing
6.1 entities and 4.9 relations were identified per code clause. These results show that compared with documents from other domains, entities appear more densely in building codes, and the relations between these entities are richer

Summary

Introduction

Automated code compliance checking is a promising alternative to manual checking that is expected to reduce time consumption, cost, and errors [1]. This approach has received extensive attention in the architectural, engineering, and construction industries for a number of applications. A typical case is to automatically review the area of a kitchen in a residential building, where the code requirement “The area of a kitchen shall not be less than 4 m2 ” should be satisfied Such an engineering constraint is hard-coded by software engineers into e-PlanCheck while the area of the kitchen is automatically calculated from a digital drawing. Named entities, such as “kitchen”, “area”, and “4 m2 ”

Objectives

Methods

Results

Conclusion