ABSTRACT
The article emphasizes the critical importance of language generation today, particularly focusing on three key aspects: Multitasking, Multilinguality, and Multimodality, which are pivotal for the Natural Language Generation community. It delves into the activities conducted within the Multi3Generation COST Action (CA18231) and discusses current trends and future perspectives in language generation.
The Multi3Generation COST Action is a collaborative project that brings together researchers from various fields, all centered around Natural Language Generation. Natural Language Generation involves using computers to generate human-like language for tasks such as translation, summarization, question-answering, and dialogue interaction, among others. The Action addresses common challenges including efficient information representation, advanced machine learning techniques, managing uncertainty in human-Natural Language Generation interactions, and using structured knowledge from diverse sources like databases, images, and videos. Its overarching goal is to make NLG beneficial to society and widely accessible by fostering collaboration between industry and academic experts. Structured into five working groups, the Action focuses on specific aspects of Natural Language Generation, such as understanding and generating different types of information, developing efficient machine learning algorithms, enhancing dialogue and conversational language generation using knowledge bases, and fostering industry collaboration and end-user engagement. With over 133 scientists from 34 countries involved, spanning disciplines from computer science to linguistics, the project promotes diversity and inclusivity, with 60% male and 40% female participants. Relevant businesses like Unbabel and JabberBrain and other AI stakeholders like the Center for Responsible AI contribute to the Action, aiming to have a broader European impact. The Multi3Generation Action prioritizes three main areas: Multitasking, Multilinguality, and Multimodality, aiming to enhance language generation in these domains to support underrepresented languages and meet diverse user needs. The article provides insights into the initiatives and planned activities of Multi3Generation, offering valuable information for those interested in NLG and shedding light on future perspectives in this field.
ABSTRACT
In this paper, we propose a framework for the automatic generation of natural language descriptions of healthcare processes using quantitative and qualitative data and medical expert knowledge. Inspired by the demand of novel ways of conveying process mining analysis results of healthcare processes (Rojas et al., 2016), our framework is based on the most widely used Data-To-Text (D2T) pipeline (Reiter, 2007) and on the usage of process mining techniques. Backed by a general model that handles process data, this framework is able to quantify attributes in time during a process life-span, recall temporal relations and waiting times between events and its possible causes and compare case (patient) attributes between groups, among other features. Through integrating fuzzy quantification techniques, our framework is able to represent relevant quantitative process information with some degree of uncertainty present on it and describe it in natural language involving uncertain terms. A real application over the Aortic Stenosis Integrated Care Process of the University Hospital of Santiago de Compostela is presented, showcasing the potential of our framework for providing natural language descriptions of healthcare processes addressed to medical experts. Following the standards of D2T systems, manual human validation was conducted for the generated natural language descriptions by fifteen medical experts in Cardiology. Validation results are very positive, since a global average of 4.07/5.00 was achieved for questions related to understandability, usefulness and impact of the natural language descriptions on the medical experts work. More precisely, results indicate i) that the modality which conveyed the information most efficiently was natural language ii) a very clear preference of texts over the usual graphic representation of process information as the way for conveying information to experts (4.28/5.00), and iii) natural language descriptions provide relevant and useful information about the process, allowing for its improvement.
