scholarly journals Computer-aided language processing: using interpretation to redefine man-machine relations

Author(s):  
L. Tanguy
Author(s):  
Zhanjun Li ◽  
Min Liu ◽  
David C. Anderson ◽  
Karthik Ramani

Nowadays computer aided tools have enabled the creation of the electronic design documents on an unprecedented scale, while determining and finding what can be reused is like searching a “needle in a haystack.” One of the primary reasons for this is that the design knowledge behind the physical design is not properly represented and indexed. With the large amount of designs available, design engineers need to retrieve suitable ones, so that a knowledge-based unified reuse environment can be realized. In this paper, we describe our approach to intelligently annotating and retrieving designs by using ontology engineering and natural language processing. We use the design documents from an engineering design class as the first case study.


Author(s):  
Tieyan Yue

Nowadays, there are more and more researches on the application of natural language processing technology in computer-aided language system, which can provide a good assistant role for foreign language learners. However, in the research of computer-aided language system, there are still some deficiencies in the recognition of English spoken stress nodes, which cannot be well recognized. Based on this, this paper proposes a method of English spoken accent recognition based on natural language processing and endpoint detection algorithm, which aims to promote the accuracy of accent recognition in the computer-aided language system and improve the performance of the computer-aided language system. In order to avoid the interference of background noise, this paper proposes a short-term time-frequency endpoint detection algorithm which can accurately judge the beginning and end of speech in complex environment. Then, on the basis of traditional speech feature extraction and fractal dimension theory, a nonlinear fractal dimension speech feature is extracted. Finally, RankNet is used to process the extracted features to realize the recognition of English spoken stress nodes. In the simulation analysis, the application effect of the short-term time-frequency endpoint detection algorithm proposed in this paper in the complex background noise and the effect of non-linear fractal dimension speech features on the recognition of English spoken stress nodes are verified. Finally, the performance and good application effect of the method designed in this paper are illustrated.


Author(s):  
Torsten Maier ◽  
Nicolas F. Soria Zurita ◽  
Elizabeth Starkey ◽  
Daniel Spillane ◽  
Jessica Menold ◽  
...  

Abstract The rapid digitalization of the world has affected engineering and design in a variety of ways, including the introduction of new computer-aided ideation tools. Cognitive assistants (CA), an increasingly common digital technology, use natural-language processing and artificial intelligence to provide computational support. Because cognitive assistants are capable of emulating humans in some tasks, they may be suited to support brainstorming activities when trained coaches or facilitators are not available. This study compared co-located brainstorming groups facilitated by human facilitators and a CA facilitator. Interaction Dynamics Notation was used to code the sessions, and Hidden Markov Models were used to define the group’s states. We found that human facilitation was associated with blocks/interruptions and responding to those while cognitive assistant facilitation was associated with deviations and silence. Human facilitation was also found to produce a more equal distribution of speaking time.


2020 ◽  
Author(s):  
Hui Chen ◽  
Honglei Liu ◽  
Ni Wang ◽  
Yanqun Huang ◽  
Zhiqiang Zhang ◽  
...  

BACKGROUND Liver cancer remains to be a substantial disease burden in China. As one of the primary diagnostic means for liver cancer, the dynamic enhanced computed tomography (CT) scan provides detailed diagnosis evidence that is recorded in the free-text radiology reports. OBJECTIVE In this study, we combined knowledge-driven deep learning methods and data-driven natural language processing (NLP) methods to extract the radiological features from these reports, and designed a computer-aided liver cancer diagnosis framework.In this study, we combined knowledge-driven deep learning methods and data-driven natural language processing (NLP) methods to extract the radiological features from these reports, and designed a computer-aided liver cancer diagnosis framework. METHODS We collected 1089 CT radiology reports in Chinese. We proposed a pre-trained fine-tuning BERT (Bidirectional Encoder Representations from Transformers) language model for word embedding. The embedding served as the inputs for BiLSTM (Bidirectional Long Short-Term Memory) and CRF (Conditional Random Field) model (BERT-BiLSTM-CRF) to extract features of hyperintense enhancement in the arterial phase (APHE) and hypointense in the portal and delayed phases (PDPH). Furthermore, we also extracted features using the traditional rule-based NLP method based on the content of radiology reports. We then applied random forest for liver cancer diagnosis and calculated the Gini impurity for the identification of diagnosis evidence. RESULTS The BERT-BiLSTM-CRF predicted the features of APHE and PDPH with an F1 score of 98.40% and 90.67%, respectively. The prediction model using combined features had a higher performance (F1 score, 88.55%) than those using the single kind of features obtained by BERT-BiLSTM-CRF (84.88%) or traditional rule-based NLP method (83.52%). The features of APHE and PDPH were the top two essential features for the liver cancer diagnosis. CONCLUSIONS We proposed a BERT-based deep learning method for diagnosis evidence extraction based on clinical knowledge. With the recognized features of APHE and PDPH, the liver cancer diagnosis could get a high performance, which was further increased by combining with the radiological features obtained by the traditional rule-based NLP method. The BERT-BiLSTM-CRF had achieved the state-of-the-art performance in this study, which could be extended to other kinds of Chinese clinical texts. CLINICALTRIAL None


2006 ◽  
Vol 12 (2) ◽  
pp. 177-194 ◽  
Author(s):  
RUSLAN MITKOV ◽  
LE AN HA ◽  
NIKIFOROS KARAMANIS

This paper describes a novel computer-aided procedure for generating multiple-choice test items from electronic documents. In addition to employing various Natural Language Processing techniques, including shallow parsing, automatic term extraction, sentence transformation and computing of semantic distance, the system makes use of language resources such as corpora and ontologies. It identifies important concepts in the text and generates questions about these concepts as well as multiple-choice distractors, offering the user the option to post-edit the test items by means of a user-friendly interface. In assisting test developers to produce items in a fast and expedient manner without compromising quality, the tool saves both time and production costs.


2019 ◽  
Author(s):  
Jingfang Liu ◽  
Xiaoyan Jiang ◽  
Wei Zhang ◽  
Yingyi Zhou

BACKGROUND Online Health Community (OHC) refers to a forum where patients, their family members, doctors and caregivers communicate with each other. Patients who participate in OHCs can obtain benefits for disease treatments and health management, so identifying the categories of patient needs and how they are satisfied are significant to determining theories of patient demand and community construction. OBJECTIVE (1) Explore the needs of patients in the Internet environment. (2) Distinguish the similarities and differences of patient needs among OHCs of different types and concerning different diseases. (3) Proposed a method for automatically identifying patient demands in Internet environments. METHODS This study used a combination of manual annotation and computer-aided method to mine value of 9936 posts collected from four OHCs in China. On one hand, we recruited 7 diabetes or depression medical experts to label text according to a theoretical framework, forming patient need theory in Internet environments, which is designed for the first two research goals. On the other hand, based on the corpus constructed by manual annotation, this research used Natural Language Processing (NLP) and Machine Learning (ML) to train a model for automatically identifying patient demands, which is planned to reach the third research purpose. RESULTS According to statistical results, the proportion of posts related to patient needs in OHCs was approximately 91%, and posts concerned with Emotional Support (18%), Information (28%) and Socialization (44%) needs were the top three most prevalent categories. However, when OHCs were divided according to user composition and disease type, patient needs were diverse: the chief demand was Socialization in Patient Interaction OHCs (65%), Diabetes OHCs (50%), and Depression OHCs (69%), while Information (96%) was the chief demand in Patient-Doctor Interaction OHCs. A model was trained to identify patient needs taking Linguistic Features (LF) and Category Keyword Features (CKF) as input and Random Forest as the classifier, of which the F1 value was higher than 0.80 on test set. CONCLUSIONS Patient needs in the Internet environment mainly include Emotional Support needs, Information needs and Socialization needs. Differences in community type and disease type can lead to diverse patient needs in OHCs. It is practical to use computer-aided methods to identify patient needs in OHCs automatically.


Sign in / Sign up

Export Citation Format

Share Document