Medical Concept systems, lexicons and Natural Language Generation

In this paper, we analyze the problem of generating fluent English utterances from tabular data, focusing on the development of a sequence-to-sequence neural model which shows two major features: the ability to read and generate character-wise, and the ability to switch between generating and copying characters from the input: an essential feature when inputs contain rare words like proper names, telephone numbers, or foreign words. Working with characters instead of words is a challenge that can bring problems such as increasing the difficulty of the training phase and a bigger error probability during inference. Nevertheless, our work shows that these issues can be solved and efforts are repaid by the creation of a fully end-to-end system, whose inputs and outputs are not constrained to be part of a predefined vocabulary, like in word-based models. Furthermore, our copying technique is integrated with an innovative shift mechanism, which enhances the ability to produce outputs directly from inputs. We assess performance on the E2E dataset, the benchmark used for the E2E NLG challenge, and on a modified version of it, created to highlight the rare word copying capabilities of our model. The results demonstrate clear improvements over the baseline and promising performance compared to recent techniques in the literature.

Download Full-text

Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment

The Science of The Total Environment ◽

10.1016/j.scitotenv.2019.03.440 ◽

2019 ◽

Vol 673 ◽

pp. 643-655 ◽

Cited By ~ 1

Author(s):

Koen Arts ◽

Christopher J.A. Macleod ◽

Antonio A.R. Ioris ◽

Xiwu Han ◽

Somayajulu Sripada ◽

...

Keyword(s):

Natural Language ◽

Information Provision ◽

Natural Language Generation ◽

Environmental Information ◽

Online Experiment ◽

Language Generation ◽

User Groups

Download Full-text

ProBot – A Procedure Chatbot for Digital Procedural Adherence

Proceedings of the Human Factors and Ergonomics Society Annual Meeting ◽

10.1177/1071181320641054 ◽

2020 ◽

Vol 64 (1) ◽

pp. 224-228

Author(s):

Nilesh Ade ◽

Noor Quddus ◽

Trent Parker ◽

S.Camille Peres

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Natural Language ◽

Industry 4.0 ◽

Natural Language Generation ◽

Conversational Agent ◽

Safe Distance ◽

Process Industries ◽

Language Generation ◽

Plastic Pellets

One of the major implications of Industry 4.0 will be the application of digital procedures in process industries. Digital procedures are procedures that are accessed through a smart gadget such as a tablet or a phone. However, like paper-based procedures their usability is limited by their access. The issue of accessibility is magnified in tasks such as loading a hopper car with plastic pellets wherein the operators typically place the procedure at a safe distance from the worksite. This drawback can be tackled in the case of digital procedures using artificial intelligence-based voice enabled conversational agent (chatbot). As a part of this study, we have developed a chatbot for assisting digital procedure adherence. The chatbot is trained using the possible set of queries from the operator and text from the digital procedures through deep learning and provides responses using natural language generation. The testing of the chatbot is performed using a simulated conversation with an operator performing the task of loading a hopper car.

Download Full-text