Natural language processing research at the University of Delaware

The review of previous works shows this study is the first attempt to analyse the lockdown effect using Natural Language Processing Techniques, particularly sentiment analysis methods applied at large scale. On the other hand, it is also the first of its kind to analyse the impact of COVID 19 on the university community jointly on staff and students and with a multi-country perspective. The main overall findings of this work show that the most often related words were family, anxiety, house and life. On another front, it has also been shown that staff have a slightly less negative perception of the consequences of COVID in their daily life. We have used artificial intelligence models like swivel embedding and the Multilayer Perceptron, as classification algorithms. The performance reached in terms of accuracy metric are 88.8% and 88.5%, for student and staff respectively. The main conclusion of our study is that higher education institutions and policymakers around the world may benefit from these findings while formulating policy recommendations and strategies to support students during this and any future pandemics.

Download Full-text

LANGUAGE LEARNING BASED PRACTICING WITH STORIES: HOW TECHNOLOGY HELPS TO TEACHER

Russkii iazyk za rubezhom ◽

10.37632/pi.2020.283.6.007 ◽

2021 ◽

pp. 50-57

Author(s):

А. Катинская ◽

Ж. Хоу ◽

Р. Янгарбер

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Learning ◽

Computational Linguistics ◽

Language Processing ◽

Language Competence ◽

Student Progress ◽

Advanced Students ◽

Educational Applications ◽

The University

Одна из перспективных областей компьютерной лингвистики – разработка образовательных приложений. В данной статье на примере системы «Ревита» показано, как инструменты для автоматического анализа текста могут быть использованы при создании сервиса для изучения языка. «Ревита» разрабатывается в Хельсинкском университете и представляет собой инструмент для автоматического создания грамматических упражнений на основе текстов, которые преподаватель или сам пользователь загружает в систему. «Ревита» предназначена для студентов среднего или продвинутого уровня; при этом упражнения подбираются для студентов с учетом их уровня подготовленности – для этого система анализирует данные о выполнении заданий каждым учеником. «Ревита» предоставляет инструменты для включения учеников в группы, с которыми учитель может легко делиться материалами, упражнениями. Также для учителя доступен режим анализа успеваемости учеников. Developing educational applications of one the promising areas of Computational Linguistics. In this article, we show how tools for automatic natural language processing can be used to create a system for language learning. Revita is being developed at the University of Helsinki. It is a tool for automatically creating exercises based on texts that the teacher or the learner can upload to the system. Revita is intended for intermediate or advanced students. Exercises are automatically selected for students considering their level of language competence. For this, the system analyzes data on the performance of tasks by each student. Revita also provides tools for including students in groups with which the teacher can easily share materials, exercises, as well as easily track a student progress.

Download Full-text

Natural Language Processing and Psychology in e-Government Services

International Journal of Electronic Government Research ◽

10.4018/ijegr.2015040101 ◽

2015 ◽

Vol 11 (2) ◽

pp. 1-17 ◽

Cited By ~ 1

Author(s):

Alicia Iriberri

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Cognitive Interview ◽

Complete Information ◽

Computer Application ◽

Face To Face ◽

Database Technology ◽

Interviewing Techniques ◽

The University

Crime statistics from the US Bureau of Justice and the FBI Uniform Crime Report show a gap between reported and unreported crime. For police to effectively prevent and solve crime, they require accurate and complete information about incidents. This article describes the evaluation of a crime reporting and interviewing system that witnesses can use to report crime incidents or suspicious activities anonymously while ensuring the information received is of such quality that police can use it to begin an investigation process. The system emulates the tasks that a police investigator would perform by leveraging natural language processing technology and the interviewing techniques used in the Cognitive Interview. The system incorporates open-source code from the General Architecture for Text Engineering (GATE) program developed by researchers at the University of Sheffield, Web and database technology, and Java-based proprietary code developed by the author. Findings of this evaluation show that the system is capable of producing accurate and complete reports by enhancing witnesses' memory recall and that its efficacy approximates the efficacy of a human conducting a cognitive interview closer than existing alternatives. The system is introduced as the first computer application of the cognitive interview and proposed as a viable alternative to face-to-face investigative interviews.

Download Full-text

Nature: A Tool Resulting from the Union of Artificial Intelligence and Natural Language Processing for Searching Research Projects in Colombia

International Journal of Artificial Intelligence & Applications ◽

10.5121/ijaia.2021.12401 ◽

2021 ◽

Vol 12 (04) ◽

pp. 01-21

Author(s):

Felipe Cujar-Rosero ◽

David Santiago Pinchao Ortiz ◽

Silvio Ricardo Timarán Pereira ◽

Jimmy Mateo Guerrero Restrepo

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Natural Language Processing ◽

Natural Language ◽

Virtual Environment ◽

Language Processing ◽

Machine Learning Algorithms ◽

Research Projects ◽

Machine Learning Model ◽

The University

This paper presents the final results of the research project that aimed for the construction of a tool which is aided by Artificial Intelligence through an Ontology with a model trained with Machine Learning, and is aided by Natural Language Processing to support the semantic search of research projects of the Research System of the University of Nariño. For the construction of NATURE, as this tool is called, a methodology was used that includes the following stages: appropriation of knowledge, installation and configuration of tools, libraries and technologies, collection, extraction and preparation of research projects, design and development of the tool. The main results of the work were three: a) the complete construction of the Ontology with classes, object properties (predicates), data properties (attributes) and individuals (instances) in Protegé, SPARQL queries with Apache Jena Fuseki and the respective coding with Owlready2 using Jupyter Notebook with Python within the virtual environment of anaconda; b) the successful training of the model for which Machine Learning algorithms were used and specifically Natural Language Processing algorithms such as: SpaCy, NLTK, Word2vec and Doc2vec, this was also performed in Jupyter Notebook with Python within the virtual environment of anaconda and with Elasticsearch; and c) the creation of NATURE by managing and unifying the queries for the Ontology and for the Machine Learning model. The tests showed that NATURE was successful in all the searches that were performed as its results were satisfactory.

Download Full-text

A New Call Laboratory

ReCALL ◽

10.1017/s0958344000002482 ◽

1991 ◽

Vol 3 (4) ◽

pp. 2-4

Author(s):

David Shaw

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Learning ◽

Language Processing ◽

Computer Assisted ◽

Computer Assisted Language Learning ◽

Teaching Laboratory ◽

Language Studies ◽

The University ◽

New Generation

After attending the 1989 Exeter CALL Conference, David Shaw and John Partridge, two teachers from the University of Kent, recommended to the School of European and Modem Language Studies that the School should establish its own Computer Assisted Language Learning Laboratory. Several of us had been ‘keeping an eye’ on CALL for quite a few years, from the days when BBC micros were innovative marvels. The Applied Languages Board had acquired a BBC and some software and had gained some experience with it in postgraduate courses. David Shaw had been supervising practical programming projects for MSc students in Computing in the area of CALL and natural language processing. Our recommendation was that, with a new generation of microcomputers supplanting the trusty but limited BBC micro, a point had been reached where it would be realistic for the School to establish a CALL teaching laboratory on a more ambitious scale.

Download Full-text

Natural Language Processing and Enhanced Clinical Decision Making Radiology and VINCI

PsycEXTRA Dataset ◽

10.1037/e615572012-015 ◽

2012 ◽

Author(s):

Eliot Siegel

Keyword(s):

Decision Making ◽

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Clinical Decision Making ◽

Clinical Decision

Download Full-text

Natural Language Processing in the Clinical Setting

PsycEXTRA Dataset ◽

10.1037/e615572012-013 ◽

2012 ◽

Author(s):

Thomas H. Payne

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Clinical Setting

Download Full-text

A Review and evaluation of Machine Translation methods for Lumasaaba

Journal of Digital Science ◽

10.33847/2686-8296.2.1_1 ◽

2020 ◽

pp. 3-17

Author(s):

Peter Nabende

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Machine Translation ◽

Language Processing ◽

Research Area ◽

Data Driven ◽

East African ◽

Data Set ◽

African Languages ◽

Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

Download Full-text