Joint Extraction of Multiple Relations and Entities from Building Code Clauses
Abstract
:1. Introduction
2. Methodology
2.1. Semantic Types of Named Entities and Relations
2.2. Joint Extraction Model
2.2.1. Model Framework
2.2.2. Augmented Character Embedding
2.2.3. Shared Semantic Encoder
2.2.4. Subject Extractor
2.2.5. Object and Predicate Extractor
2.3. Model Training and Inference
Algorithm 1 Inference Algorithm. |
Input: S S denotes the input claus Output: {} denotes the i-th extracted subject entity; and are the j-th predicate relation and object entity, respectively, associated with the i-th subject entity.
|
3. Experiment
3.1. Data Preparation and Labeling
3.2. Implementation of the Joint Extraction Model
3.3. Experimental Results and Analysis
4. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Eastman, C.; Lee, J.; Jeong, Y.; Lee, J. Automatic rule-based checking of building designs. Autom. Constr. 2009, 18, 1011–1033. [Google Scholar] [CrossRef]
- Kim, I.; Lee, Y.; Choi, J. BIM-based hazard recognition and evaluation methodology for automating construction site risk assessment. Appl. Sci. 2020, 10, 2335. [Google Scholar] [CrossRef] [Green Version]
- Jiang, S.; Wu, Z.; Zhang, B.; Cha, H.S. Combined MvdXML and semantic technologies for green construction code checking. Appl. Sci. 2019, 9, 1463. [Google Scholar] [CrossRef] [Green Version]
- Lee, Y.; Kim, I.; Choi, J. Development of BIM-based risk rating estimation automation and a design-for-safety review system. Appl. Sci. 2020, 10, 3902. [Google Scholar] [CrossRef]
- Zhong, B.; Gan, C.; Luo, H.; Xing, X. Ontology-based framework for building environmental monitoring and compliance checking under BIM environment. Build. Environ. 2018, 141, 127–142. [Google Scholar] [CrossRef]
- CORENET e-PlanCheck: Singapore’s Automated Code Checking System. Available online: http://www.aecbytes.com/feature/2005/CORENETePlanCheck.html (accessed on 25 September 2020).
- Zhong, B.; Ding, L.; Luo, H.; Zhou, Y.; Hu, Y.; Hu, H. Ontology-based semantic modeling of regulation constraint for automated construction quality compliance checking. Autom. Constr. 2012, 28, 58–70. [Google Scholar] [CrossRef]
- Zhang, J.; El-Gohary, N.M. Semantic NLP-based information extraction from construction regulatory documents for automated compliance checking. J. Comput. Civ. Eng. 2016, 30, 04015014. [Google Scholar] [CrossRef] [Green Version]
- Zhang, J.; El-Gohary, N.M. Integrating semantic NLP and logic reasoning into a unified system for fully-automated code checking. Autom. Constr. 2017, 73, 45–57. [Google Scholar] [CrossRef] [Green Version]
- Zhou, P.; El-Gohary, N.M. Ontology-based automated information extraction from building energy conservation codes. Autom. Constr. 2017, 74, 103–117. [Google Scholar] [CrossRef]
- Li, S.; Cai, H.; Kamat, V.R. Integrating natural language processing and spatial reasoning for utility compliance checking. J. Constr. Eng. Manag. 2016, 142, 04016074. [Google Scholar] [CrossRef]
- Xu, X.; Cai, H. Semantic approach to compliance checking of underground utilities. Autom. Constr. 2017, 109, 103006. [Google Scholar] [CrossRef]
- Zhang, R.; El-Gohary, N.M. A machine learning approach for compliance checking-specific semantic role labeling of building code sentences. In Proceedings of the 35th International Conference of CIB W78, Chicago, IL, USA, 1–3 October 2018; pp. 561–568. [Google Scholar]
- Xu, X.; Cai, H. Semantic frame-based information extraction from utility regulatory documents to support compliance checking. In Proceedings of the 35th International Conference of CIB W78, Chicago, IL, USA, 1–3 October 2018; pp. 223–230. [Google Scholar]
- Petruck, M.R.; Ellsworth, M. Representing spatial relations in FrameNet. In Proceedings of the First International Workshop on Spatial Language Understanding, New Orleans, LA, USA, 12–16 June 2018; pp. 41–45. [Google Scholar]
- Papadopoulos, D.; Papadakis, N.; Litke, A. A methodology for open information extraction and representation from large scientific corpora: The CORD-19 data exploration use case. Appl. Sci. 2020, 10, 5630. [Google Scholar] [CrossRef]
- Wang, Y.; Sun, Y.; Ma, Z.; Gao, L.; Xu, Y. An ERNIE-based joint model for Chinese named entity recognition. Appl. Sci. 2020, 10, 5711. [Google Scholar] [CrossRef]
- Song, J.; Kim, J.; Lee, J. NLP and deep learning-based analysis of building regulations to support automated rule checking system. In Proceedings of the 35th International Symposium on Automation and Robotics in Construction, Berlin, Germany, 23–25 July 2018; pp. 586–592. [Google Scholar]
- Mikolov, T.; Chen, K.; Corrado, G.; Dean, J. Efficient estimation of word representations in vector space. In Proceedings of the First International Conference on Learning Representations, Scottsdale, AZ, USA, 2–4 May 2013. [Google Scholar]
- Song, J.; Lee, J.; Choi, J.; Kim, I. Deep learning-based extraction of predicate-argument structure (PAS) in building design rule sentences. J. Comput. Des. Eng. 2020, 7, 1–14. [Google Scholar]
- Zhong, B.; Xing, X.; Luo, H.; Zhou, Q.; Li, H.; Rose, T.; Fang, W. Deep learning-based extraction of construction procedural constraints from construction regulations. Adv. Eng. Inform. 2020, 43, 101003. [Google Scholar] [CrossRef]
- He, C.; Tan, Z.; Wang, H.; Zhang, C.; Hu, Y.; Ge, B. Open domain Chinese triples hierarchical extraction method. Appl. Sci. 2020, 10, 4819. [Google Scholar] [CrossRef]
- Lehmann, J.; Isele, R.; Jakob, M.; Jentzsch, A.; Kontokostas, D.; Mendes, P.; Hellmann, S.; Morsey, M.; Van Kleef, P.; Auer, S.; et al. DBpedia—A large-scale, multilingual knowledge base extracted from wikipedia. Semant. Web. 2015, 6, 167–195. [Google Scholar] [CrossRef] [Green Version]
- Al Qady, M.; Kandil, A. Concept relation extraction from construction documents using natural language processing. J. Constr. Eng. Manag. 2010, 136, 294–302. [Google Scholar] [CrossRef]
- Xiong, R.; Song, Y.; Li, H.; Wang, Y. Onsite video mining for construction hazards identification with visual relationships. Adv. Eng. Inform. 2019, 42, 100966. [Google Scholar] [CrossRef]
- International Organization for Standardization. ISO 12006-2: 2015. Building Construction. Organization of Information about Construction Works. Part 2: Framework for Classification of Information, 2nd ed.; International Organization for Standardization: Geneva, Switzerland, 2015. [Google Scholar]
- Xiao, S.; Song, M. A text-generated method to joint extraction of entities and relations. Appl. Sci. 2019, 9, 3795. [Google Scholar]
- Tan, Z.; Zhao, X.; Wang, W.; Xiao, W. Jointly extracting multiple triplets with multilayer translation constraints. In Proceedings of the AAAI Conference on Artificial Intelligence; Association for the Advancement of Artificial Intelligence (AAAI), Honolulu, HI, USA, 27 January–1 February 2019; pp. 7080–7087. [Google Scholar]
- Dai, D.; Xiao, X.; Lyu, Y.; Dou, S.; She, Q.; Wang, H. Joint extraction of entities and overlapping relations using position-attentive sequence labeling. In Proceedings of the AAAI Conference on Artificial Intelligence; Association for the Advancement of Artificial Intelligence (AAAI), Honolulu, HI, USA, 27 January–1 February 2019; pp. 6300–6308. [Google Scholar]
- Fu, T.; Li, P.; Ma, W. GraphRel: Modeling text as relational graphs for joint entity and relation extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July–2 August 2019; pp. 1409–1418. [Google Scholar]
- Yu, B.; Zhang, Z.; Su, J. Joint extraction of entities and relations based on a novel decomposition strategy. arXiv 2019, arXiv:1909.04273. [Google Scholar]
- MOHURD. Standard for Classification and Coding of Building Information Model (GB/T51269-2017); China Architecture & Building Press: Beijing, China, 2017. [Google Scholar]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 8–14 December 2017; pp. 6000–6010. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Ren, X.; Wu, Z.; He, W.; Qu, M.; Voss, C.R.; Ji, H.; Abdelzaher, T.F.; Han, J. Cotype: Joint extraction of typed entities and relations with knowledge bases. In Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, 3–7 May 2017; pp. 1015–1024. [Google Scholar]
- Zheng, S.; Wang, F.; Bao, H.; Hao, Y.; Zhou, P.; Xu, B.; Barzilay, R.; Kan, M.Y. Joint extraction of entities and relations based on a novel tagging scheme. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, BC, Canada, 30 July–4 August 2017. [Google Scholar]
- Zeng, X.; Zeng, D.; He, S.; Liu, K.; Zhao, J. Extracting relational facts by an end-to-end neural model with copy mechanism. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, 15–20 July 2018. [Google Scholar]
Entity Category | Label | Example |
---|---|---|
Building | E | residential building |
Built space | E | kitchen |
Construction element | E | wall |
Feature | E | accessible |
Property | E | height |
Quantity | E | 4.0 m |
Relation Category | Predicate | Label | Semantic Role | Example | |
---|---|---|---|---|---|
Subject | Object | ||||
System hierarchy | hasObject | R | E | E,E | [building, hasObject, wall] |
E | E,E | [toilet, hasObject, window] | |||
E | E | [stair, hasObject, step] | |||
Engineering property | hasProperty | R | E,E,E | E | [kitchen, hasProperty, area] |
Function and purpose | hasFeature | R | E,E,E | E | [entrance, hasFeature, accessible] |
Spatial relationship | Within | R | E,E,E | E,E | [pipeline, Within, building] |
Outside | R | E,E,E | E,E | [fire hydrant, Outside, tunnel] | |
Between | R | E,E,E,E | E,E,E | [clearance, Between, wall] | |
AdjacentTo | R | E,E,E | E,E,E | [road, AdjacentTo, entrance] | |
AccessTo | R | E,E,E | E,E,E | [corridor, AccessTo, bedroom] | |
Comparative relation | NotLessThan | R | E | E,E | [height, NotLessThan, 2 m] |
NotGreaterThan | R | E | E,E | [height, NotGreaterThan, 2 m] | |
LessThan | R | E | E,E | [height, LessThan, 2 m] | |
GreaterThan | R | E | E,E | [height, GreaterThan, 2 m] | |
EqualTo | R | E | E,E | [height, EqualTo, 2 m] | |
Quantity reference | MultipliedBy | R | E | E | [area, MultipliedBy, 1/2] |
Standard No. | Name of Chinese Building Codes |
---|---|
GB50368-2005 | 《住宅建筑规范》(Residential building code) |
GB50096-2011 | 《住宅设计规范》(Design code for residential buildings) |
GB50352-2019 | 《民用建筑设计统一标准》(Uniform standard for the design of civil buildings) |
GB50763-2012 | 《无障碍设计规范》(Code for accessibility design) |
GB50016-2014 | 《建筑设计防火规范》(Code for the fire protection design of buildings) |
GB50099-2011 | 《中小学校设计规范》(Code for the design of schools) |
GB51039-2014 | 《综合医院建筑设计规范》(Code for the design of general hospitals) |
GB50067-2014 | 《公共建筑节能设计标准》(Design standard for the energy efficiency of public buildings) |
GB50038-2005 | 《人民防空地下室设计规范》(Code for the design of civil air defense basements) |
JGJ100-2015 | 《车库建筑设计规范》(Code for the design of parking garage buildings) |
JGJ450-2018 | 《老年人照料设施建筑设计标准》(Standard for the design of care facilities for the aged) |
JGJ39-2016 | 《托儿所、幼儿园建筑设计规范》(Code for the design of nursery and kindergarten buildings) |
JGJ48-2014 | 《商店建筑设计规范》(Code for the design of store buildings) |
JGJ62-2014 | 《旅馆建筑设计规范》(Code for the design of hotel buildings) |
Predicate Type | In Gold Standard | Extracted | Correctly Extracted | Precision | Recall | F-Measure |
---|---|---|---|---|---|---|
hasObject | 305 | 298 | 243 | 0.8154 | 0.7967 | 0.8060 |
hasProperty | 406 | 388 | 357 | 0.9201 | 0.8793 | 0.8992 |
hasFeature | 279 | 266 | 240 | 0.9023 | 0.8602 | 0.8807 |
AccessTo | 26 | 19 | 17 | 0.8947 | 0.6538 | 0.7556 |
Within | 42 | 44 | 38 | 0.8636 | 0.9048 | 0.8837 |
Outside | 21 | 15 | 13 | 0.8667 | 0.6190 | 0.7222 |
Between | 115 | 108 | 95 | 0.8796 | 0.8261 | 0.8520 |
AdjacentTo | 30 | 23 | 21 | 0.9130 | 0.7000 | 0.7925 |
NotLessThan | 278 | 290 | 266 | 0.9172 | 0.9568 | 0.9366 |
NotGreaterThan | 78 | 77 | 69 | 0.8961 | 0.8846 | 0.8903 |
LessThan | 26 | 27 | 18 | 0.6667 | 0.6923 | 0.6792 |
GreaterThan | 27 | 27 | 19 | 0.7037 | 0.7037 | 0.7037 |
EqualTo | 17 | 20 | 14 | 0.7001 | 0.8235 | 0.7568 |
MultipliedBy | 24 | 17 | 16 | 0.9412 | 0.6667 | 0.7805 |
Total | 1674 | 1619 | 1426 | 0.8808 | 0.8519 | 0.8661 |
Model | Precision | Recall | F-Measure |
---|---|---|---|
Ren et al. [36] | 0.3748 | 0.3202 | 0.3454 |
Zheng et al. [37] | 0.5039 | 0.4253 | 0.4613 |
Tan et al. [28] | 0.6704 | 0.6099 | 0.6387 |
Zeng et al. [38] | 0.7098 | 0.6780 | 0.6936 |
Fu et al. [30] | 0.7440 | 0.7640 | 0.7539 |
Our Model | 0.8808 | 0.8519 | 0.8661 |
Model | Precision | Recall | F-Measure |
---|---|---|---|
Whole Model | 0.8808 | 0.8519 | 0.8661 |
-word-level embedding | 0.8535 | 0.8005 | 0.8261 |
-character-level embedding | 0.8647 | 0.8094 | 0.8362 |
-sentence-level features | 0.8692 | 0.8136 | 0.8404 |
-start tagging features | 0.8582 | 0.8065 | 0.8315 |
-joint learning | 0.8287 | 0.7772 | 0.8021 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, F.; Song, Y.; Shan, Y. Joint Extraction of Multiple Relations and Entities from Building Code Clauses. Appl. Sci. 2020, 10, 7103. https://doi.org/10.3390/app10207103
Li F, Song Y, Shan Y. Joint Extraction of Multiple Relations and Entities from Building Code Clauses. Applied Sciences. 2020; 10(20):7103. https://doi.org/10.3390/app10207103
Chicago/Turabian StyleLi, Fulin, Yuanbin Song, and Yongwei Shan. 2020. "Joint Extraction of Multiple Relations and Entities from Building Code Clauses" Applied Sciences 10, no. 20: 7103. https://doi.org/10.3390/app10207103
APA StyleLi, F., Song, Y., & Shan, Y. (2020). Joint Extraction of Multiple Relations and Entities from Building Code Clauses. Applied Sciences, 10(20), 7103. https://doi.org/10.3390/app10207103