Event Log Construction from Customer Service Conversations Using Natural Language Inference

Titelangaben

Kecht, Christoph ; Egger, Andreas ; Kratsch, Wolfgang ; Röglinger, Maximilian:
Event Log Construction from Customer Service Conversations Using Natural Language Inference.
In: Proceedings of the 3rd International Conference on Process Mining (ICPM). - Piscataway, USA , 2021 . - S. 144-151
ISBN 978-1-6654-3514-7

Volltext

Link zum Volltext (externe URL):

Angaben zu Projekten

Abstract

A fundamental requirement for the successful application
of process mining are event logs of high data quality that
can be constructed from structured data stored in organizations’core information systems. However, a substantial amount of datais processed outside these core systems, particularly in organizations doing consumer business with many customer interactions per day, which generate high amounts of unstructured text data. Although Natural Language Processing (NLP) and machine
learning enable the exploitation of text data, these approachesremain challenging due to the required high amount of labeledtraining data. Recent advances in NLP mitigate this issue byproviding pre-trained and ready-to-use language models forvarious tasks such as Natural Language Inference (NLI). In thispaper, we develop an approach that utilizes NLI to derive topicsand process activities from customer service conversations andthat represents them in a standardized XES event log. To this end,
we compute the probability that a sentence describing the topic orthe process activity can be inferred from the customer’s inquiry or the agent’s response using NLI. We evaluate our approach utilizing an existing corpus of more than 500,000 customer service conversations of three companies on Twitter. The results show that NLI helps construct event logs of high accuracy for process
mining purposes, as our successful application of three different process discovery algorithms confirms.