Abstract
The extraction of business processes elements from textual documents is a research area which still lacks the ability to scale to the variety of real-world texts. In this paper we investigate the usage of pre-trained language models and in-context learning to address the problem of information extraction from process description documents as a way to exploit the power of deep learning approaches while relying on few annotated data. In particular, we investigate the usage of the native GPT-3 model and few in-context learning customizations that rely on the usage of conceptual definitions and a very limited number of examples for the extraction of typical business process entities and relationships. The experiments we have conducted provide two types of insights. First, the results demonstrate the feasibility of the proposed approach, especially for what concerns the extraction of activity, participant, and the performs relation between a participant and an activity it performs. They also highlight the challenge posed by control flow relations. Second, it provides a first set of lessons learned on how to interact with these kinds of models that can facilitate future investigations on this subject.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We have chosen BPMN as an illustrative example but the approach is clearly agnostic to the specific modeling language.
- 2.
The terminology for these instructions varies from paper to paper.
- 3.
The interested reader can found all the PET-related resources at http://huggingface.co/datasets/patriziobellan/PET.
- 4.
The “activity” label is used in PET only to represent the verbal component of what is usually denoted as business process activity.
- 5.
Several definitions exist of many business process elements (see e.g., www.businessprocessglossary.com), but they often present different wordings and even conflicting characteristics [4]. A thorough investigation of the impact of different definitions of business process elements is out of the goal of this paper and is left for future works.
- 6.
In few cases the model was able to provide semantically correct answers which did not match the exact PET labels. A paradigmatic case is the answer “check and repair the computer” as a single activity, instead of the two separate ones which are reported PET, as required by its specific annotation guidelines. We have carefully considered these few cases and decided to evaluate the semantically correct answers as correct answers.
References
van der Aa, H., Carmona, J., Leopold, H., Mendling, J., Padró, L.: Challenges and opportunities of applying natural language processing in business process management. In: COLING 2018 Proceedings of 27th International Conference on Computational Linguistics, pp. 2791–2801. ACL (2018)
van der Aa, H., Di Ciccio, C., Leopold, H., Reijers, H.A.: Extracting declarative process models from natural language. In: Giorgini, P., Weber, B. (eds.) CAiSE 2019. LNCS, vol. 11483, pp. 365–382. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-21290-2_23
Ackermann, L., Volz, B.: model[NL]generation: natural language model extraction. In: Proceedings of the 2013 ACM workshop DSM@SPLASH 2013, pp. 45–50. ACM (2013)
Adamo, G., Di Francescomarino, C., Ghidini, C.: Digging into business process meta-models: a first ontological analysis. In: Dustdar, S., Yu, E., Salinesi, C., Rieu, D., Pant, V. (eds.) CAiSE 2020. LNCS, vol. 12127, pp. 384–400. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49435-3_24
Bellan, P., van der Aa, H., Dragoni, M., Ghidini, C., Ponzetto, S.P.: PET: an annotated dataset for process extraction from natural language text tasks. In: Proceedings of the BPM 2022 First Workshop on Natural Language Processing for Business Process Management (NLP4BPM) co-located with the 20th conference Business Process Management, CEUR Workshop Proceedings. CEUR-WS.org (2022)
Bellan, P., Dragoni, M., Ghidini, C.: Process extraction from text: state of the art and challenges for the future. CoRR abs/2110.03754 (2021)
Boratko, M., Li, X., O’Gorman, T., Das, R., Le, D., McCallum, A.: ProtoQA: a question answering dataset for prototypical common-sense reasoning. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, pp. 1122–1136. ACL (2020)
Brown, T.B., et al.: Language models are few-shot learners. In: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020 (2020)
Chintagunta, B., Katariya, N., Amatriain, X., Kannan, A.: Medically aware GPT-3 as a data generator for medical dialogue summarization. In: Proceedings of the 6th Machine Learning for Healthcare Conference, Proceedings of Machine Learning Research, vol. 149, pp. 354–372. PMLR (2021)
Chiu, K., Alexander, R.: Detecting hate speech with GPT-3. CoRR abs/2103.12407 (2021)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT 2019, Vol. 1, pp. 4171–4186. ACL (2019)
Epure, E.V., Martín-Rodilla, P., Hug, C., Deneckère, R., Salinesi, C.: Automatic process model discovery from textual methodologies. In: 9th IEEE International Conference on Research Challenges in Information Science, RCIS 2015, pp. 19–30. IEEE (2015)
Ferreira, R.C.B., Thom, L.H., Fantinato, M.: A Semi-automatic approach to identify business process elements in natural language texts. In: ICEIS 2017 - Proceedings of the 19th International Conference on Enterprise Information Systems, Vol. 3, pp. 250–261. SciTePress (2017)
Friedrich, F., Mendling, J., Puhlmann, F.: Process model generation from natural language text. In: Mouratidis, H., Rolland, C. (eds.) CAiSE 2011. LNCS, vol. 6741, pp. 482–496. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21640-4_36
Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. In: Proceedings of ACL/IJCNLP 2021, pp. 3816–3830. ACL (2021)
Han, X., et al.: A-BPS: automatic business process discovery service using ordered neurons LSTM. In: 2020 IEEE International Conference on Web Services, ICWS 2020, pp. 428–432. IEEE (2020)
Honkisz, K., Kluza, K., Wiśniewski, P.: A concept for generating business process models from natural language description. In: Liu, W., Giunchiglia, F., Yang, B. (eds.) KSEM 2018. LNCS (LNAI), vol. 11061, pp. 91–103. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99365-2_8
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. ArXiv abs/1907.11692 (2019)
López, H.A., Debois, S., Hildebrandt, T.T., Marquard, M.: The process highlighter: from texts to declarative processes and back. In: Proceedings of Dissertation Award, Demo, and Industrial Track, BPM 2018. CEUR Workshop Proceedings, vol. 2196, pp. 66–70. CEUR-WS.org (2018)
Maqbool, B., et al.: A comprehensive investigation of BPMN models generation from textual requirements—techniques, tools and trends. In: Kim, K.J., Baek, N. (eds.) ICISA 2018. LNEE, vol. 514, pp. 543–557. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-1056-0_54
Petrucci, G., Rospocher, M., Ghidini, C.: Expressive ontology learning as neural machine translation. J. Web Semant. 52–53, 66–82 (2018)
Qian, C., et al.: An approach for process model extraction by multi-grained text classification. In: Dustdar, S., Yu, E., Salinesi, C., Rieu, D., Pant, V. (eds.) CAiSE 2020. LNCS, vol. 12127, pp. 268–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49435-3_17
Quishpi, L., Carmona, J., Padró, L.: Extracting annotations from textual descriptions of processes. In: Fahland, D., Ghidini, C., Becker, J., Dumas, M. (eds.) BPM 2020. LNCS, vol. 12168, pp. 184–201. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58666-9_11
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1–140:67 (2020)
Sànchez-Ferreres, J., Burattin, A., Carmona, J., Montali, M., Padró, L., Quishpi, L.: Unleashing textual descriptions of business processes. Softw. Syst. Model. 20(6), 2131–2153 (2021). https://doi.org/10.1007/s10270-021-00886-x
Sawant, K.P., Roy, S., Sripathi, S., Plesse, F., Sajeev, A.S.M.: Deriving requirements model from textual use cases. In: 36th International Conference on Software Engineering, ICSE 2014, Proceedings, pp. 235–244. ACM (2014)
Scao, T.L., Rush, A.M.: How many data points is a prompt worth? In: Proceedings of NAACL-HLT 2021, pp. 2627–2636. ACL (2021)
Wang, S., Liu, Y., Xu, Y., Zhu, C., Zeng, M.: Want to reduce labeling cost? GPT-3 can help. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 4195–4205. ACL (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bellan, P., Dragoni, M., Ghidini, C. (2022). Extracting Business Process Entities and Relations from Text Using Pre-trained Language Models and In-Context Learning. In: Almeida, J.P.A., Karastoyanova, D., Guizzardi, G., Montali, M., Maggi, F.M., Fonseca, C.M. (eds) Enterprise Design, Operations, and Computing. EDOC 2022. Lecture Notes in Computer Science, vol 13585. Springer, Cham. https://doi.org/10.1007/978-3-031-17604-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-17604-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17603-6
Online ISBN: 978-3-031-17604-3
eBook Packages: Computer ScienceComputer Science (R0)