A code-mixed task-oriented dialog dataset for medical domain. (March 2023)

• Record Type: Journal Article
• Authors: Dowlagar, Suman; Mamidi, Radhika
• Is Part Of: Computer speech & language. Volume 78(2023)
• Publication Date: 2023-03
• Subjects: Code-mixed -- Dialog dataset -- Medical domain -- Task oriented; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2022.101449
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: In the healthcare domain, medical and patient interactions form a crucial part of the diagnosis. Initially, the AI models developed for healthcare centered only on monolingual data. However, such models do not cater to the multilingual regions, where most conversations are Code-Mixed. We present the Code-Mixed Medical Task-Oriented Dialog Dataset to facilitate the research and development of Code-Mixed medical dialog systems. We analyzed the dataset using medical, conversational, and linguistic theories. The dataset contains 3005 Telugu–English Code-Mixed dialogs between patients and doctors with 29 k utterances covering ten specializations with an average code-mixing index (CMI) of 33.3%. We manually annotated the conversational dataset with intents and slot labels. We also present baselines to establish benchmarks on the dataset using existing state-of-the-art Natural Language Understanding (NLU) models. We improved the existing baselines using contextual ground truth intent labels and processing the slots as chunks. The data is made publically available. 1 Graphical abstract: Highlights: It is the first corpus containing Code-Mixed medical conversations in the Telugu–English language. The dialogs are taken from real-life conversations. To understand the user's utterance, we annotated the corpus with intents and slots. We ran the baseline NLU models to establish a benchmark on our task-oriented corpus. We also proposed an improvement over the baseline NLU models.