Arabic Question Classification Using Support Vector Machines and Convolutional Neural Networks
14
Citation
20
Reference
10
Related Paper
Citation Trend
The question answering system is an essential task of natural language processing. In recent years, the deep neural network has made remarkable achievements in many fields. It has reached a level close to human beings in many applications, such as image classification. However, due to the particularity of the question-answering task, the question answering system close to the intelligence level is still a challenge. Firstly, this paper reviews the development of a question answering system, including the Turing Test and traditional question answering systems. Then, the advanced question answering system at present is introduced and analyzed in detail. In addition, we discussed the challenges faced by the current question answering system and puts forward some constructive solutions, including the bottleneck of statistical learning methods, data privacy, and other issues.
Constructive
Turing test
Cite
Citations (4)
Question Answering (QA) is a focused way of information retrieval. Question Answering system tries to get back the accurate answers to questions posed in natural language provided a set of documents. Basically question answering system (QA) has three elements i.e. question classification, information retrieval (IR), and answer extraction. These elements play a major role in Question Answering. In Question classification, the questions are classified depending upon the type of its entity. Information retrieval component is used to determine success by retrieving relevant answer for different questions posted by the intelligent question answering system. Answer extraction module is growing topics in the QA in which ranking and validating a candidate’s answer is the major job. This paper offers a concise discussion regarding different Question Answering types. In addition we describe different evaluation metrics used to evaluate the performance of different question answering systems. We also discuss the recent question answering systems developed and their corresponding techniques.
Component (thermodynamics)
Cite
Citations (5)
We describe the architecture of the AskMSR question answering system and systematically evaluate contributions of different system components to accuracy. The system differs from most question answering systems in its dependency on data redundancy rather than sophisticated linguistic analyses of either questions or candidate answers. Because a wrong answer is often worse than no answer, we also explore strategies for predicting when the question answering system is likely to give an incorrect answer.
Questions and answers
Cite
Citations (321)
A simple question answering system is presented in this paper. Question answering system is a very difficult research topic, which is related to knowledge representation,information retrieval and natural language processing. This paper describes three components for question processing,retrieval system,answer extraction. Key words:Question answering system;
Representation
Cite
Citations (4)
An Information Retrieval(IR) system is established to solve the validation of relevant documents in Question Answering for Chinese Question Answering and the related NTCIR-7 meeting is introduced in this paper.The system optimizes the query by question type of Question Answering to improve the quality during document retrieval.In the dependent evaluation of IR,the mean average precision is 0.5013;In the Question Answering evaluation,the F3 score is 0.2231.sounds a good performance in Question Answering.
Cite
Citations (0)
We present an efficient and accurate long-form question-answering platform, dubbed iLFQA (i.e., short for intelligent Long-Form Question Answering). The purpose of iLFQA is to function as a platform which accepts unscripted questions and efficiently produces semantically meaningful, explanatory, and accurate long-form responses. iLFQA consists of a number of modules for zero-shot classification, text retrieval, and text generation to generate answers to questions based on an open-domain knowledge base. iLFQA is unique in the question answering space because it is an example of a deployable and efficient long-form question answering system. Question answering systems exist in many forms, but long-form question answering remains relatively unexplored, and to the best of our knowledge none of the existing long-form question answering systems are shown to be sufficiently efficient to be deployable. We have made the source code and implementation details of iLFQA available for the benefit of researchers and practitioners in this field. With this demonstration, we present iLFQA as an open-domain, deployable, and accurate open-source long-form question answering platform.
Open domain
Cite
Citations (2)
Question Answering is a hot research field in Natural Language Processing,which includes many kinds of NLP technology.This paper introduces the current research status and the methods that are often used in Question Answering.In general,a Question Answering system is made up of three parts:Question Analysis,Information Retrieval and Answer Extraction.This paper describes the main functions of these three parts and the common approach used in these parts in detail.At last,this paper introduces the evaluation of Question Answering system.
Cite
Citations (36)
Representation
Cite
Citations (1)
Recently, question and answering systems have attracted lots of attention. Given a question, the goal of question and answering is to return a concise, exact answer. According to the format of data, question and answering can be divided into three categories: the structural data based question and answering, the free-text based question and answering, the question-answer pairs based question and answering. This paper describes and summarizes the characteristics and related researches of these three categories respectively. Then, it discusses the future work of question and answering.
Cite
Citations (7)
2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA) (2020)
The field of text mining which deals with the providing of answers to the questions of the users is also one of the hot topics for researchers. The difficulty seen in the proper answering of the questions needs to be resolved. The large variety of questions fails in the QA system. In this paper, Natural Language Processing (NLP) has been used which deals with the processing of the data that comes in any form like text, video, image, or audio. This NLP comes under the field of artificial intelligence (AI), which is used in the field of question answering (QA) system. Here proposed work for designing a system that works for factoid QA which will answer the questions that are asked by the users. Lexical Chain and Keyword analysis are used in our system for the answering of questions from a given set of articles. The reasoning system is used for the validity of the answering. The experiment here is done with the SQUAD dataset. In our experiment, the accuracy obtained for the passage retrieval using TFIDF is 69.69%. The overall average of the correct prediction of the answer is 69.93%.
Cite
Citations (6)