Towards a Natural Language Conversational Interface for Process Mining (original) (raw)

Bootstrapping Natural Language Querying on Process Automation Data

2020

Advances in the adoption of business process management platforms have led to increasing volumes runtime event logs, containing information about the execution of the process. Business users analyze this event data for real-time insights on performance and optimization opportunities. However, querying the event data is difficult for business users without knowing the details of the backend store, data schema, and query languages. Consequently, the business insights are mostly limited to static dashboards, only capturing predefined performance metrics. In this paper, we introduce an interface for business users to query the business event data using natural language, without knowing the exact schema of the event data or the query language. Moreover, we propose a bootstrapping pipeline, which utilizes both event data and business domain-specific artifacts to automatically instantiate the natural language interface over the event data. We build and evaluate our prototype over datasets ...

NLP as a Service: An API to Convert between Process Models and Natural Language Text

2021

An interesting extension of contemporary BPM tools is the ability to export graphical process models into natural language and vice versa, i.e. to mine a graphical process model from a description in natural language. Both transformations are computationally complex Natural Language Processing (NLP) problems and usually require elaborated algorithms, data structures, and IT resources. This contribution describes the architecture of a platform providing NLP-based conversion in both directions as a service, i.e. via a public webservice interface, addressing BPM users or modelers as well as software engineers aiming to add NLP features to existing BPM tools.

Generating Natural-language Process Descriptions from Formal Process Definitions

2011

Process models are often used to support the understanding and analysis of complex systems. The accuracy of such process models usually requires that domain experts carefully review, evaluate, correct, and propose improvements to these models. Domain experts, however, are often not experts in process modeling and may not even have any programming experience. Consequently, domain experts may not have the skills to understand the process models except at a relatively supercial level. To address this issue, we have developed an approach for automatically generating natural-language process descriptions based on formal process models. Unlike natural language process descriptions in existing electronic process guides, these process descriptions are generated completely automatically and can describe complex process features, such as exception handling, concurrency, and non-determinisitc choice. The generated process descriptions have been well-received by domain experts from several dier...

Process Extraction from Natural Language Text

2020

Public and private organizations always seek to achieve high standardization and improve performance of their business processes. Having control over business times, costs, errors and redundancy is vital to survive from continuous business revolutions [18, 31]. Business ProcessManagement is a discipline that aims to discover, analyze, and optimize business processes, typically represented in model diagrams. Unfortunately, the initial elicitation of a process model from documents is a time consuming and cost intensive operation, as argued in [15, 21]. Therefore, companies and the scientific community are interested in discovering novel algorithmic procedures to alleviate the initial creation of process models from documents. The extraction of a process model from documents is a complex task since the analysis of the natural language description of a process may produce multiple interpretation. This task is made up of three main activities. Filtering uninformative sentences of the pro...

WoPeD goes NLP: Conversion between Workflow Nets and Natural Language

2018

WoPeD (Workflow Petrinet Designer) is an open-source Java software for designing business processes in terms of workflow nets, a common extension of Petri nets. This demo lays the focus on two recently added features making use of Natural Language Processing (NLP) algorithms in order support the conversion of a graphical process model into a textual process description and vice versa.

Declo: A Chatbot for User-friendly Specification of Declarative Process Models

2020

Proposed approaches for modeling knowledge-intensive processes include declarative, constraint-based solutions, which meet halfway between support and flexibility. A noteworthy example is the Declare framework, which is equipped with a graphical declarative language whose semantics can be expressed with multiple logic-based formalisms. So far, the practical use of Declare constraints has been mostly hampered by the difficulty of modeling them: the formal notation of Declare represents a steep learning curve for users lacking an understanding of temporal logic, while the graphical notation has proven to be unintuitive. This work presents Declo, a chatbot that allows users to easily define declarative constraints using natural language statements provided in the form of vocal or textual input. The supported constraints cover the entire Multi-Perspective extension of Declare (MP-Declare), complementing control-flow constraints with data and temporal perspectives.

Process-To-Text: a framework for the quantitative description of processes in natural language

In this paper we present the Process-To-Text (P2T) framework for the automatic generation of textual descriptive explanations of business processes in natural language. P2T integrates three AI paradigms: process mining for extracting temporal and structural information from a process, fuzzy linguistic protoforms for modelling uncertain terms and natural language generation for building the explanations. A real usecase in the medical domain is presented, showing the potential of P2T for providing natural language explanations addressed to cardiology specialists.