scholarly journals Graphical Interface for the Recommendation System

2021 ◽  
Vol 4 ◽  
pp. 93-97
Author(s):  
Oleksii Dymchenko ◽  
Oleh Smysh ◽  
Oleksandr Zhezherun
Keyword(s):  
Programming Languages ◽  
Language Processing ◽  
Recommendation System ◽  
Intermediate Stage ◽  
Simple Problem ◽  
Graphical Interface ◽  
Open Type ◽  
Interface Module ◽  
Written Form ◽  
Processing Module

Today, mathematics plays a huge part of our everyday life. But due to the poor school education and lack of open access resources, many students find it difficult to be fully prepared for the independent external evaluation in mathematics, especially geometry. Although much has already been done to conduct higher knowledge results, lots of students still have gaps in understanding simple problem solving. Clearly, geometry requires a more fundamental and visual implementation to the studying process than algebra in order to increase the overall knowledge level of Ukrainian applicants for higher education. Students often do not have access to innovative studying instruments in their schools necessary for successful completion of geometry classes, which is why they receive weak results in tests.In the research, we are concentrating on the planimetry problems, because they can be easily produced in a written form. After analyzing all types of describing a problem, the best option for the system is the open-type problems with the short answer.The article concentrates on creating a graphical interface module, implementing it to the existing language processing module, and introducing a recommendation system that demonstrates a new fundamental instrument that can change the learning technique and give a comprehensive way of explaining geometry problems.The created system receives an open-type planimetry problem in Ukrainian language, processes it using the NLP module, and transfers the data directly to the interface module, which creates an image of the problem. Then the student can try to draw all the required figures, while the system continuously checks the progress. Recommendations (hints) can be applied during the process by the system.Interface and the NLP modules were created separately, independently, and using different programming languages. For that purpose, we use an intermediate stage – JSON file, which is used to transfer the processed information.

scholarly journals Automated Source Code Generation and Auto-Completion Using Deep Learning: Comparing and Discussing Current Language Model-Related Approaches

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 1-16
Author(s):  
Juan Cruz-Benito ◽  
Sanjay Vishwakarma ◽  
Francisco Martin-Fernandez ◽  
Ismael Faro
Keyword(s):  
Deep Learning ◽  
Learning Community ◽  
Programming Languages ◽  
Language Processing ◽  
Code Generation ◽  
Language Model ◽  
Language Models ◽  
Stochastic Gradient Descent ◽  
Network Architectures ◽  
Learning Architectures

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach’s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context.

Multi-modal referring expressions in human-human task descriptions and their implications for human-robot interaction

2016 ◽  
Vol 17 (2) ◽  
pp. 180-210
Author(s):  
Stephanie Gross ◽  
Brigitte Krenn ◽  
Matthias Scheutz
Keyword(s):  
Language Processing ◽  
Eye Gaze ◽  
Human Robot Interaction ◽  
Referring Expressions ◽  
Visual Channel ◽  
Student Interactions ◽  
Seamless Integration ◽  
Teacher Student ◽  
Processing Module ◽  
Task Descriptions

Abstract Human instructors often refer to objects and actions involved in a task description using both linguistic and non-linguistic means of communication. Hence, for robots to engage in natural human-robot interactions, we need to better understand the various relevant aspects of human multi-modal task descriptions. We analyse reference resolution to objects in a data collection comprising two object manipulation tasks (22 teacher student interactions in Task 1 and 16 in Task 2) and find that 78.76% of all referring expressions to the objects relevant in Task 1 are verbally underspecified and 88.64% of all referring expressions are verbally underspecified in Task 2. The data strongly suggests that a language processing module for robots must be genuinely multi-modal, allowing for seamless integration of information transmitted in the verbal and the visual channel, whereby tracking the speaker’s eye gaze and gestures as well as object recognition are necessary preconditions.

scholarly journals xml2jupyter: Mapping parameters between XML and Jupyter widgets

2019 ◽  
Author(s):  
Randy Heiland ◽  
Daniel Mishler ◽  
Tyler Zhang ◽  
Eric Bower ◽  
Paul Macklin
Keyword(s):  
Programming Languages ◽  
Markup Language ◽  
Command Line ◽  
Graphical Interface ◽  
Web Browser ◽  
Agent Based ◽  
Mapping Parameters ◽  
Extensible Markup ◽  
Parameter Values ◽  
Python Package

AbstractJupyter Notebooks [4, 6] provide executable documents (in a variety of programming languages) that can be run in a web browser. When a notebook contains graphical widgets, it becomes an easy-to-use graphical user interface (GUI). Many scientific simulation packages use text-based configuration files to provide parameter values and run at the command line without a graphical interface. Manually editing these files to explore how different values affect a simulation can be burdensome for technical users, and impossible to use for those with other scientific backgrounds. xml2jupyter is a Python package that addresses these scientific bottlenecks. It provides a mapping between configuration files, formatted in the Extensible Markup Language (XML), and Jupyter widgets. Widgets are automatically generated from the XML file and these can, optionally, be incorporated into a larger GUI for a simulation package, and optionally hosted on cloud resources. Users modify parameter values via the widgets, and the values are written to the XML configuration file which is input to the simulation’s command-line interface. xml2jupyter has been tested using PhysiCell [1], an open source, agent-based simulator for biology, and it is being used by students for classroom and research projects. In addition, we use xml2jupyter to help create Jupyter GUIs for PhysiCell-related applications running on nanoHUB [5].

Knowledge-Based Task Planning Using Natural Language Processing for Robotic Manufacturing

2010 ◽  
Author(s):  
Iraj Mantegh ◽  
Nazanin S. Darbandi
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Programming Languages ◽  
Language Processing ◽  
New Method ◽  
Robot Programming ◽  
Task Planning ◽  
End User ◽  
Knowledge Based ◽  
Manufacturing Applications

Robotic alternative to many manual operations falls short in application due to the difficulties in capturing the manual skill of an expert operator. One of the main problems to be solved if robots are to become flexible enough for various manufacturing needs is that of end-user programming. An end-user with little or no technical expertise in robotics area needs to be able to efficiently communicate its manufacturing task to the robot. This paper proposes a new method for robot task planning using some concepts of Artificial Intelligence. Our method is based on a hierarchical knowledge representation and propositional logic, which allows an expert user to incrementally integrate process and geometric parameters with the robot commands. The objective is to provide an intelligent and programmable agent such as a robot with a knowledge base about the attributes of human behaviors in order to facilitate the commanding process. The focus of this work is on robot programming for manufacturing applications. Industrial manipulators work with low level programming languages. This work presents a new method based on Natural Language Processing (NLP) that allows a user to generate robot programs using natural language lexicon and task information. This will enable a manufacturing operator (for example for painting) who may be unfamiliar with robot programming to easily employ the agent for the manufacturing tasks.

Question Answering

2012 ◽  
Author(s):  
Sanda Harabagiu ◽  
Dan Moldovan
Keyword(s):  
Language Processing ◽  
Question Answering ◽  
Document Retrieval ◽  
Semantic Features ◽  
Knowledge Based ◽  
Answer Extraction ◽  
Small Set ◽  
Processing Module ◽  
On Line ◽  
Processing Techniques

Textual Question Answering (QA) identifies the answer to a question in large collections of on-line documents. By providing a small set of exact answers to questions, QA takes a step closer to information retrieval rather than document retrieval. A QA system comprises three modules: a question-processing module, a document-processing module, and an answer extraction and formulation module. Questions may be asked about any topic, in contrast with Information Extraction (IE), which identifies textual information relevant only to a predefined set of events and entities. The natural language processing (NLP) techniques used in open-domain QA systems may range from simple lexical and semantic disambiguation of question stems to complex processing that combines syntactic and semantic features of the questions with pragmatic information derived from the context of candidate answers. This article reviews current research in integrating knowledge-based NLP methods with shallow processing techniques for QA.

The Modularity of Sentence Processing Reconsidered

2017 ◽  
Author(s):  
Fernanda Ferreira ◽  
James Nye
Keyword(s):  
Language Processing ◽  
Sentence Processing ◽  
Sentence Comprehension ◽  
Experimental Investigations ◽  
Modular Architecture ◽  
New Findings ◽  
Modular Architectures ◽  
Processing Module ◽  
Almost All

Today, the modular view of sentence processing is unpopular, but the arguments against modularity are not as strong as this apparent consensus would suggest. Almost all experimental investigations of modularity have focused on properties pertaining to information encapsulation, and most of those studies have evaluated just one specific modular architecture. A review of these studies of sentence comprehension suggests that the evidence against information encapsulation is really evidence against that one architecture only, and a whole range of other possible modular architectures remain untested. Although psycholinguistic work has largely ignored the modularity claims relating to shallow outputs, new findings from studies to test “good enough” language processing suggest that the output of the language processing module can be characterized as shallow or minimal. Perhaps, then, the modularity hypothesis was prematurely rejected. Evidence for shallow outputs provides intriguing new support for the idea that sentence processing is indeed modular.

scholarly journals ГРАФІЧНИЙ ІНТЕРФЕЙС ЯК ДИДАКТИЧНИЙ КОМПОНЕНТ ЕЛЕКТРОННОГО ПІДРУЧНИКА

2018 ◽  
Vol 67 (5) ◽  
pp. 1
Author(s):  
Oleksandr M. Romanukha
Keyword(s):  
Programming Languages ◽  
Information Technologies ◽  
Cognitive Activity ◽  
Scientific Progress ◽  
Modern Society ◽  
Model Description ◽  
Graphical Interface ◽  
The World ◽  
Human Thinking ◽  
The Individual

This article deals with the issue of updating the principles of creation of e-textbooks via graphical interface. The close attention has to be paid to the transformation of the modern society where the new generation of people uses computers, smartphones and tablets not only as working tools but as the means of discovering the world as well. Therefore the graphical interface is considered the code of understanding the information environment. It is emphasised that the spread of information technologies and information transmission and processing methods have become an integral element of human thinking and perception of the world. Getting most of their information through the Internet modern people perceive process and memorize it according to the principles of the interface and programming languages. In this regard graphical interface is seen as the fundamental of the e-textbook visualization. The article presents the model description of the e-textbook “History of Ukraine” visualized as the cube. Each tier in this cube describes the cultural stratum of the epoch and shows the general dynamics of historical development. Each plane in this cube analyses the content of each problem. Studying every part, students open consistently the horizontal cube stratums and see the topics of the epoch represented by the graphical interface device. Every topic contains visualized scheme with hyperactive dates and surnames with zero traditional text with hyperlinks. The advantage of such e-textbook structure is to rise student cognitive activity due to the new principles of the educational material visualization. The e-textbook interface is intuitive; it can be updated and used to get the insight into selected topics and questions. It has means to activate the resources of human higher nervous system taking into account the individual features of students and topics they are studying. Attention is drawn to the fact that scientific progress has been made possible largely thanks to the improvement of semiotics, that is, the development of our language, especially those of its branches, as the language of symbolic logic, rather than by improving brain function.

Sign in / Sign up

Export Citation Format

Share Document