A KNOWLEDGE-BASED CHINESE LETTER-WRITER

Author(s):  
KOH TOH TZU

Since the end of last year, the researchers at the Institute of Systems Science (ISS) started to consider a more ambitious project as part of its multilingual programming objective. This project examines the domain of Chinese Business Letter Writing. With the problem defined as generating Chinese letters to meet business needs, investigations suggest an intersection of 3 possible approaches: knowledge engineering, form processing and natural language processing. This paper attempts to report some of the findings and document the design and implementation issues that have arisen and been tackled as prototyping work progresses.

Author(s):  
Saravanakumar Kandasamy ◽  
Aswani Kumar Cherukuri

Semantic similarity quantification between concepts is one of the inevitable parts in domains like Natural Language Processing, Information Retrieval, Question Answering, etc. to understand the text and their relationships better. Last few decades, many measures have been proposed by incorporating various corpus-based and knowledge-based resources. WordNet and Wikipedia are two of the Knowledge-based resources. The contribution of WordNet in the above said domain is enormous due to its richness in defining a word and all of its relationship with others. In this paper, we proposed an approach to quantify the similarity between concepts that exploits the synsets and the gloss definitions of different concepts using WordNet. Our method considers the gloss definitions, contextual words that are helping in defining a word, synsets of contextual word and the confidence of occurrence of a word in other word’s definition for calculating the similarity. The evaluation based on different gold standard benchmark datasets shows the efficiency of our system in comparison with other existing taxonomical and definitional measures.


Author(s):  
Azleena Mohd Kassim ◽  
Yu-N Cheah

Information Technology (IT) is often employed to put knowledge management policies into operation. However, many of these tools require human intervention when it comes to deciding how the knowledge is to be managed. The Sematic Web may be an answer to this issue, but many Sematic Web tools are not readily available for the regular IT user. Another problem that arises is that typical efforts to apply or reuse knowledge via a search mechanism do not necessarily link to other pages that are relevant. Blogging systems appear to address some of these challenges but the browsing experience can be further enhanced by providing links to other relevant posts. In this chapter, the authors present a semantic blogging tool called SEMblog to identify, organize, and reuse knowledge based on the Sematic Web and ontologies. The SEMblog methodology brings together technologies such as Natural Language Processing (NLP), Sematic Web representations, and the ubiquity of the blogging environment to produce a more intuitive way to manage knowledge, especially in the areas of knowledge identification, organization, and reuse. Based on detailed comparisons with other similar systems, the uniqueness of SEMblog lies in its ability to automatically generate keywords and semantic links.


2020 ◽  
Author(s):  
Pablo Sierra

Abstract We first define a language for the dialogical logic and the models that the language generates. This language is thought to capture the structure of the dialogues captured by Lekta—a software framework oriented to the design and implementation of natural language processing-related applications—and its users. These dialogues are defined as cooperative dialogues in which the dialogical logic perspective of a dialogue seen as a competition is shifted into a perspective in which both agents cooperate towards a common goal. Later we define a BDI temporal logic based on a modal framework that we will use to study the beliefs, desires and intentions of both agents based on the model generated by the dialogical logic.


Author(s):  
Iraj Mantegh ◽  
Nazanin S. Darbandi

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.


Author(s):  
J. A. Rodger ◽  
P. C. Pendharkar

The case study describes the process of planning, analysis, design and implementation of an integrated voice interactive device (VID) for the Navy. The goal of this research is to enhance Force Health Protection and to improve medical readiness by applying voice interactive technology to environmental and clinical surveillance activities aboard U.S. Navy ships.


Author(s):  
Xiaoyu Lin ◽  
Yingxu Wang

Concept algebra (CA) is a denotational mathematics for formal knowledge manipulation and natural language processing. In order to explicitly demonstrate the mathematical models of formal concepts and their algebraic operations in CA, a simulation and visualization software is developed in the MATLAB environment known as the Visual Simulator of Concept Algebra (VSCA). This paper presents the design and implementation of VSCA and the theories underpinning its development. Visual simulations for the sets of reproductive and compositional operations of CA are demonstrated by real-world examples throughout the elaborations of CA and VSCA.


Author(s):  
Roy Rada

The techniques of artificial intelligence include knowledgebased, machine learning, and natural language processing techniques. The discipline of investing requires data identification, asset valuation, and risk management. Artificial intelligence techniques apply to many aspects of financial investing, and published work has shown an emphasis on the application of knowledge-based techniques for credit risk assessment and machine learning techniques for stock valuation. However, in the future, knowledge-based, machine learning, and natural language processing techniques will be integrated into systems that simultaneously address data identification, asset valuation, and risk management.


Sign in / Sign up

Export Citation Format

Share Document