A Review on Question Generation from Natural Language Text

2022 ◽  
Vol 40 (1) ◽  
pp. 1-43
Author(s):  
Ruqing Zhang ◽  
Jiafeng Guo ◽  
Lu Chen ◽  
Yixing Fan ◽  
Xueqi Cheng
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Data Augmentation ◽  
Text Structure ◽  
Current Status ◽  
Question Generation ◽  
Natural Language Text ◽  
Question Answering Systems ◽  
The Right ◽  
Language Text

Question generation is an important yet challenging problem in Artificial Intelligence (AI), which aims to generate natural and relevant questions from various input formats, e.g., natural language text, structure database, knowledge base, and image. In this article, we focus on question generation from natural language text, which has received tremendous interest in recent years due to the widespread applications such as data augmentation for question answering systems. During the past decades, many different question generation models have been proposed, from traditional rule-based methods to advanced neural network-based methods. Since there have been a large variety of research works proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we try to provide a more comprehensive taxonomy of question generation tasks from three different perspectives, i.e., the types of the input context text, the target answer, and the generated question. We take a deep look into existing models from different dimensions to analyze their underlying ideas, major design principles, and training strategies We compare these models through benchmark tasks to obtain an empirical understanding of the existing techniques. Moreover, we discuss what is missing in the current literature and what are the promising and desired future directions.

scholarly journals Event Extraction and Classification from English Articles

2019 ◽  
Vol 8 (2) ◽  
pp. 2861-2865
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Event Extraction ◽  
Natural Language Text ◽  
Digital World ◽  
Accuracy Measure ◽  
Question Answering Systems ◽  
English Articles ◽  
Information Finding ◽  
Language Text

Today’s digital world huge number of information sources like wikis, web, blogs and other sources are creating a lot of information with several events. Basically, an event can be a situation, action or state that can be represented in natural language text in the form of happening or occurrence. Analyzing the event information finding the relation between the events is one of the crucial tasks in information retrieval. In a formal way, the event can be defined as a real-world entity that happens or occur; these are the dynamic occurrences which have causes or effects (E.g. earthquake, floods, crime, etc.). Extracting events, events fall within a timelines extraction can be applied in many of the natural language applications like text summarization, temporal question answering systems, etc. Event extraction and classification can use in other related text searches like News domains, legal documents, wikis, manuscripts, and time-based searches. In this paper, we present a methodology for event extraction in natural language text which helps in finding out the type of an event and classifies the events under specific categories. Our work aims to develop a system which would automatically identify events from articles generated over the internet. The system would not only detect the events but also tried to detect important times of the event. Finally compared the accuracy of work with several classifiers and obtained results shows good accuracy measure for Support Vectors machine (SVM).

scholarly journals Declarative Question Answering over Knowledge Bases Containing Natural Language Text with Answer Set Programming

2019 ◽  
Vol 33 ◽  
pp. 3003-3010 ◽  
Author(s):  
Arindam Mitra ◽  
Peter Clark ◽  
Oyvind Tafjord ◽  
Chitta Baral
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Answer Set Programming ◽  
Knowledge Bases ◽  
Logical Reasoning ◽  
Natural Language Text ◽  
Question Answering Systems ◽  
Logical Representation ◽  
Language Text ◽  
Answer Set

While in recent years machine learning (ML) based approaches have been the popular approach in developing endto-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to 18% performance gain when compared to standard MCQ solvers.

scholarly journals Sentence Extraction for Machine Comprehension

2019 ◽  
Vol 8 (2) ◽  
pp. 5511-5514
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Research Area ◽  
Performance Comparison ◽  
Word Count ◽  
Natural Language Text ◽  
Sentence Extraction ◽  
The Given ◽  
Language Text

Machine comprehension is a broad research area from Natural Language Processing domain, which deals with making a computerised system understand the given natural language text. Question answering system is one such variant used to find the correct ‘answer’ for a ‘query’ using the supplied ‘context’. Using a sentence instead of the whole context paragraph to determine the ‘answer’ is quite useful in terms of computation as well as accuracy. Sentence selection can, therefore, be considered as a first step to get the answer. This work devises a method for sentence selection that uses cosine similarity and common word count between each sentence of context and question. This removes the extensive training overhead associated with other available approaches, while still giving comparable results. The SQuAD dataset is used for accuracy based performance comparison.

scholarly journals Event Time Relationship in Natural Language Text

2019 ◽  
Vol 7 (3) ◽  
pp. 4
Author(s):  
Vanitha Guda ◽  
SureshKumar Sanampudi
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Information Needs ◽  
Question Answering ◽  
Data Set ◽  
Natural Language Text ◽  
Event Time ◽  
The Given ◽  
Events Data ◽  
Language Text

<p>Due to the numerous information needs, retrieval of events from a given natural language text is inevitable. In natural language processing (NLP) perspective, "Events" are situations, occurrences, real-world entities or facts. Extraction of events and arranging them on a timeline is helpful in various NLP application like building the summary of news articles, processing health records, and Question Answering System (QA) systems. This paper presents a framework for identifying the events and times from a given document and representing them using a graph data structure.  As a result, a graph is derived to show event-time relationships in the given text. Events form the nodes in a graph, and edges represent the temporal relations among the nodes. Time of an event occurrence exists in two forms namely qualitative (like before, after, duringetc) and quantitative (exact time points/periods). To build the event-time-event structure quantitative time is normalized to qualitative form. Thus obtained temporal information is used to label the edges among the events. Data set released in the shared task EvTExtract of (Forum for Information Retrieval Extraction) FIRE 2018 conference is identified to evaluate the framework. Precision and recall are used as evaluation metrics to access the performance of the proposed framework with other methods mentioned in state of the art with 85% of accuracy and 90% of precision.</p>

scholarly journals Event -Time Relation in Natural Language Text

2019 ◽  
Vol 8 (6) ◽  
pp. 716-724
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Information Needs ◽  
Question Answering ◽  
Data Set ◽  
Natural Language Text ◽  
Event Time ◽  
The Given ◽  
Events Data ◽  
Language Text

Due to the numerous information needs, retrieval of events from a given natural language text is inevitable. In natural language processing(NLP), "Events" are situations, occurrences, real-world entities or facts. Extraction of events and arranging them on a timeline is helpful in various NLP applications like building the summary of news articles, processing health records, and Question Answering System (QA) systems. This paper presents a framework for identifying the events and times from a given document and representing them using a graph data structure. As a result, a graph is derived to show event-time relationships in the given text. Events form the nodes in a graph, and edges represent the temporal relations among the nodes. Time of an event occurrence exists in two forms namely qualitative (like before, after, during, etc.) and quantitative (exact time points/periods). To build the event-time-event structure quantitative time is normalized to qualitative form. Thus obtained temporal information is used to label the edges among the events. Data set released in the shared task EvTExtract of (Forum for Information Retrieval Extraction) FIRE 2018 conference is identified to evaluate the framework. Precision and recall are used as evaluation metrics to access the performance of the work with other methods mentioned in state of the art with 85% of accuracy and 90% of precision.

scholarly journals AN AUTOMATIC WEB-BASED QUESTION ANSWERING SYSTEM FOR E-LEARNING

2017 ◽  
Vol 58 (2) ◽  
pp. 1
Author(s):  
Waheeb Ahmed ◽  
Babu Anto
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Web Based ◽  
Question Answering System ◽  
Natural Language Text ◽  
Exact Answer ◽  
E Learning ◽  
Language Text ◽  
Develop Technique

An automatic web based Question Answering (QA) system is a valuable tool for improving e-learning and education. Several approaches employ natural language processing technology to understand questions given in natural language text, which is incomplete and error-prone. In addition, instead of extracting exact answer, many approaches simply return hyperlinks to documents containing the answers, which is inconvenient for the students or learners. In this paper we develop technique to detect the type of a question, based on which the proper technique for extracting the answer is used. The system returns only blocks or phrases of data containing the answer rather than full documents. Therefore, we can highly improve the efficiency of Web QA systems for e-learning.

Morality Classification in Natural Language Text

2020 ◽  
pp. 1-1
Author(s):  
Matheus C. Pavan ◽  
Vitor G. Santos ◽  
Alex G. J. Lan ◽  
Joao Martins ◽  
Wesley Ramos Santos ◽  
...  
Keyword(s):  
Natural Language ◽  
Natural Language Text ◽  
Language Text

scholarly journals Composing Questions through Conceptual Authoring

2007 ◽  
Vol 33 (1) ◽  
pp. 105-133 ◽  
Author(s):  
Catalina Hallett ◽  
Donia Scott ◽  
Richard Power
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Free Text ◽  
Risk Averse ◽  
Proof Of Concept ◽  
Concept System ◽  
Complex Queries ◽  
Extensive Training ◽  
Question Answering Systems ◽  
Medical Histories

This article describes a method for composing fluent and complex natural language questions, while avoiding the standard pitfalls of free text queries. The method, based on Conceptual Authoring, is targeted at question-answering systems where reliability and transparency are critical, and where users cannot be expected to undergo extensive training in question composition. This scenario is found in most corporate domains, especially in applications that are risk-averse. We present a proof-of-concept system we have developed: a question-answering interface to a large repository of medical histories in the area of cancer. We show that the method allows users to successfully and reliably compose complex queries with minimal training.

Sign in / Sign up

Export Citation Format

Share Document