Ontology-based workflow extraction from texts using word sense disambiguation

Abstract

This paper introduces a method for automatic workflow extraction from texts using Process-Oriented Case-Based Reasoning (POCBR). While the current workflow management systems implement mostly different complicated graphical tasks based on advanced distributed solutions (e.g. cloud computing and grid computation), workflow knowledge acquisition from texts using case-based reasoning represents more expressive and semantic cases representations. We propose in this context, an ontology-based workflow extraction framework to acquire processual knowledge from texts. Our methodology extends classic NLP techniques to extract and disambiguate tasks in texts. Using a graph-based representation of workflows and a domain ontology, our extraction process uses a context-based approach to recognize workflow components : data and control flows. We applied our framework in a technical domain in bioinformatics : i.e. phylogenetic analyses. An evaluation based on workflow semantic similarities on a gold standard proves that our approach provides promising results in the process extraction domain. Both data and implementation of our framework are available in : http://labo.bioinfo.uqam.ca/tgrowler.

An Approach for Process Model Extraction by Multi-grained Text Classification

“…Recently, some knowledge based methods [10,12,13] have been applied to this problem and they were shown to perform well. For example, [12] proposed an ontology-based workflow extraction framework that extended classic NLP techniques to extract and disambiguate tasks in texts.…”

“…Recently, some knowledge based methods [10,12,13] have been applied to this problem and they were shown to perform well. For example, [12] proposed an ontology-based workflow extraction framework that extended classic NLP techniques to extract and disambiguate tasks in texts. Using a modelbased representation of workflows and a domain ontology, the extraction process used a context-based approach to recognize workflow components such as data and control elements in a flow.…”

“…Using a modelbased representation of workflows and a domain ontology, the extraction process used a context-based approach to recognize workflow components such as data and control elements in a flow. However, they also require a large quantity of cognition-level knowledge, such as a world model [8,10] or an ontology [12,13], which would be time-consuming and labor-intensive to build.…”

“…Recent research efforts have been made to extract the main procedural knowledge. For example, language-rule based extractors [12] used pre-defined language rules to extract procedural knowledge. Pattern-matching based extractors [26] used NLP tagging or parsing tools to analyze sentences and extract corresponding information from triggered patterns.…”

“…Pattern-matching based extractors [26] used NLP tagging or parsing tools to analyze sentences and extract corresponding information from triggered patterns. Knowledge-based extractors employed pre-defined ontology [12] or world model [8] to help extract that information. However, traditional methods suffer from weak generalizability when applied in open-domain or open-topic scenarios since they: 1) require much large-scale and domain-specific procedural features; and 2) ignore the relations between sentence-level and word-level subtasks.…”