SSL-QA: Analysis of Semi-Supervised Learning for QuestionAnswering
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2017, Vol 19, Issue 3
Abstract
Open domain natural language question answering (QA) is a process of automatically finding answers to questions searching collections of text files. Question answering (QA) is a long-standing challenge in NLP, and the community has introduced several paradigms and datasets for the task over the past few years. These patterns differ from each other in the type of questions and answers and the size of the training data, from a few hundreds to millions of examples. Context-aware QA paradigm and two most notable types of supervisions are coarse sentence-level and fine-grained span-level. In this paper we analyse different intensive researches in semi-supervised learning for question-answering.
Authors and Affiliations
Parth Patel, Jignesh Prajapati
Keywords
Related Articles
- EP ID EP384791
- DOI 10.9790/0661-1903051415.
- Views 99
- Downloads 0
Study of e-Governance initiatives: e-Procurement a Business Reform Process for Odisha’s Development
Abstract: Odisha is the one of the 29 states of India located in the eastern coast. Odisha which is the eleventh largest state of India in population, is working to provide better services to all the citizens in a transp...
Role of Operational System Design in Data Warehouse Implementation: Identifying the Operational System Design Gaps and techniques to handle them
Abstract: Data warehouse designing process takes input from operational system of the organization. Quality of data warehousing solution depends on design of operational system. Often, operational system implementations...
Using Artificial Intelligence Techniques For Epilepsy Treatment
Abstract: Epilepsy is a combination of neurological disorders that causes people to have seizure. Immediate seizures occurring might cause injuries of the patients or other. Recent studies of epilepsy are based on two ap...
Protection of Direct and Indirect Discrimination using Prevention Methods
Along with privacy, discrimination is a very important issue when considering the legal and ethical aspects of data mining. It is more than observable that the majority people do not want to be discriminated &nbs...
A Comparative Study of Contrast Enhancement using Image Fusion
Abstract: Image enhancement is used to improve the visual quality of an image. In this paper a different approach on image fusion has been described for image enhancement. The two main algorithms involved in this...