ABSTRACT
Online learning has gained a tremendous popularity in the last decade due to the facility to learn anytime, anything, anywhere from the ocean of web resources available. Especially the lockdown all over the world due to the Covid-19 pandemic has brought an enormous attention towards the online learning for value addition and skills development not only for the school/college students, but also to the working professionals. This massive growth in online learning has made the task of assessment very tedious and demands training, experience and resources. Automatic Question generation (AQG) techniques have been introduced to resolve this problem by deriving a question bank from the text documents. However, the performance of conventional AQG techniques is subject to the availability of large labelled training dataset. The requirement of deep linguistic knowledge for the generation of heuristic and hand-crafted rules to transform declarative sentence into interrogative sentence makes the problem further complicated. This paper presents a transfer learning-based text to text transformation model to generate the subjective and objective questions automatically from the text document. The proposed AQG model utilizes the Text-to-Text-Transfer-Transformer (T5) which reframes natural language processing tasks into a unified text-to-text-format and augments it with word sense disambiguation (WSD), ConceptNet and domain adaptation framework to improve the meaningfulness of the questions. Fast T5 library with beam-search decoding algorithm has been used here to reduce the model size and increase the speed of the model through quantization of the whole model by Open Neural Network Exchange (ONNX) framework. The keywords extraction in the proposed framework is performed using the Multipartite graphs to enhance the context awareness. The qualitative and quantitative performance of the proposed AQG model is evaluated through a comprehensive experimental analysis over the publicly available Squad dataset. © 2023, International Journal of Advanced Computer Science and Applications. All Rights Reserved.
ABSTRACT
In dialectology, Natural Language Processing is the process of recognizing the various ontologies of words generated in human language. Various techniques are used for analyzing the corpus from naturally generated content by users on various platforms. The analysis of these textual contents collected during the COVID-19 has become a goldmine for marketing experts as well as for researchers, thus making social media comments available on various platforms like Facebook, Twitter, YouTube, etc., a popular area of applied artificial intelligence. Text-Based Analysis is measured as one of the exasperating responsibilities in Natural Language Processing (NLP). The chief objective of this paper is to work on a corpus that generates relevant information from web-based statements during COVID-19. The findings of the work may give useful insights to researchers working on Text analytics, and authorities concerning to current pandemic. To achieve this, NLP is discussed which extracts relevant information and comparatively computes the morphology on publicly available data thus concluding knowledge behind the corpus. © 2022, Springer Nature Switzerland AG.
ABSTRACT
The enormous spreading of social network media like Twitter is speeding up the process of sharing information and expressing opinions about global health crises, and important events. Due to the use of different terms for expressing the same topic in a Twitter post, it becomes difficult to build applications such as retrieval of information by following previous mining methods to find a match between words or sentences. In order to solve this problem, it requires providing the knowledge source that collects many terms which reflect a single meaning, Such as ontology. Ontology is the process of representing the concepts of a specific field such as finance or epidemics, with their characteristics and relationships by dealing with the heterogeneity and complexity of terms. In this paper, the domain ontology for Twitter’s Covid-19 post will be developed by following the notion of semantic web layer cake and discuss the depth of terms and relationships extracted in this domain through a set of measurements, the ontology contains more than 900 single concepts and more than 180 multi-word concepts, which are the most concepts used in Twitter posts with the hashtag Corona epidemic which can be used to find semantic similarities between words and sentences. © 2021, Springer Nature Switzerland AG.