Narrow Results

Centering Theory assumes that entities realized in an utterance can be ranked according to their relative salience degree. This ranking called Cf-ranking (ranking of forward-looking centers) determines the likelihood that the entities realized in an utterance will be the center of the subsequent utterance, and it is one of the central issues in Centering literatures. This paper deals with these Cf-ranking issues in Korean at the level of text structuring and pronominalization for coherent text generation. For text structuring, we compare several Cf-ranking methods by examining various Centering-based metrics to evaluate local coherence of text, and for pronominalization, we compare them by examining previous rules for Centering-based pronoun generation rules and our pronominalization model. In almost all previous works, surface word order was not solely employed for Cf-ranking, instead it was additionally considered to supplement the main ranking scheme based on the fact that linear order does not perform well alone. However, this study shows that due to the characteristics of the Korean language, ranking by surface word order is better than any other ranking method in most Centering-based Metrics which depend on Cf-ranking, and it is also reliable in terms of pronominalization accuracy. Additionally we found that based on the Cf-ranking by surface word order, it is the most effective way for text structuring to maximize simply the number of utterance pairs whose first realized nominal entity in adjacent utterances is identical.

Telehealth is the usage of digital medical data and telecommunication technologies to aid long-distance clinical healthcare. Proper maintenance of a patient’s medical record has been a hindrance toward the growth of Telehealth services. The patient’s data, particularly emergency data, must be available to medical personnel within a short time frame and independent of potential interruption of network connections. In this paper, we propose a Near Field Communication (NFC) wristband that provides access to the medical details, history and contact details of a patient. By this, the doctor or the paramedical officer can provide the patient with the best treatment within a short period of time. This system comes in handy even if the patient is unconscious/unable to answer. The doctor or the paramedical officer can quickly draft a patient’s report and send it to the hospital. The proposed framework consists of the following four stages: (i) obtaining emergency medical data with the help of NFC chips, (ii) converting medical report into digital text using Optical Character Recognition (OCR), (iii) structuring the narrative medical text into organized data using NLP and (iv) comparative analysis of the selected content. An image database with 1200 medical case histories has been utilized for the algorithm development and validation. The OCR algorithms for converting images to text produced more than 98% on average and NLP algorithm produced around 94.1% accuracy. Overall, the performance of the system from NFC reader till analysis of the specific field is more than 95%. The developed OCR and NLP integrated software helps the doctor or the health officer to immediately convert it into text format and the unstructured text is quickly organized into the respective fields.