Two-stage Text-to-BIMQL semantic parsing for building information model extraction using graph neural networks

doi:10.1016/j.autcon.2023.104902

Details of Research Outputs

Title	Two-stage Text-to-BIMQL semantic parsing for building information model extraction using graph neural networks
Creator	Yin，Mengtian 1; Tang，Llewellyn 1; Webster，Chris 2; Li，Jinyang 3; Li，Haotian 1; Wu，Zhuoquan 1; Cheng，Reynold C.K.3,4,5
Date Issued	2023-08-01
Source Publication	Automation in Construction
ISSN	0926-5805
Volume	152
Abstract	With the increasing complexity of the building process, it is difficult for project stakeholders to retrieve large and multi-disciplinary building information models (BIMs). A natural language interface (NLI) is beneficial for users to query BIM models using natural language. However, parsing natural language queries (NLQs) is challenging due to ambiguous name descriptions and intricate relationships between entities. To address these issues, this study proposes a graph neural network (GNN)-based semantic parsing method that automatically maps NLQs into executable queries. Firstly, ambiguous mentions are collectively linked to referent ontological entities via a GNN-based entity linking model. Secondly, the logical forms of NLQs are interpreted through a GNN-based relation extraction model, which predicts links between mentioned entities in a heterogeneous graph fusing ontology and NLQ texts. The experiment based on 786 queries shows its outstanding performance. Moreover, a real-world case verifies the practicability of the proposed method for BIM model retrieval.
DOI	10.1016/j.autcon.2023.104902
URL	View source
Language	英语English
Scopus ID	2-s2.0-85154584328
Citation statistics	Cited Times:8[WOS] [WOS Record] [Related Records in WOS]
Document Type	Journal article
Identifier	http://repository.uic.edu.cn/handle/39GCC9TT/11870
Collection	Research outside affiliated institution
Corresponding Author	Tang，Llewellyn
Affiliation	1.Department of Real Estate and Construction,The University of Hong Kong,Hong Kong 2.Faculty of Architecture,The University of Hong Kong,Hong Kong 3.Department of Computer Science,The University of Hong Kong,Hong Kong 4.Guangdong–Hong Kong-Macau Joint Laboratory,China 5.HKU Musketeers Foundation Institute of Data Science,Hong Kong
Recommended Citation GB/T 7714	Yin，Mengtian,Tang，Llewellyn,Webster，Chriset al. Two-stage Text-to-BIMQL semantic parsing for building information model extraction using graph neural networks[J]. Automation in Construction, 2023, 152.
APA	Yin，Mengtian., Tang，Llewellyn., Webster，Chris., Li，Jinyang., Li，Haotian., .. & Cheng，Reynold C.K. (2023). Two-stage Text-to-BIMQL semantic parsing for building information model extraction using graph neural networks. Automation in Construction, 152.
MLA	Yin，Mengtian,et al."Two-stage Text-to-BIMQL semantic parsing for building information model extraction using graph neural networks". Automation in Construction 152(2023).

Files in This Item:
There are no files associated with this item.

Related Services

Usage statistics

Google Scholar

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh