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 108
- Downloads 0
A survey on recommendation system
Abstract: In this paper, we give a brief introduction about recommendation systems, components of recommendation systems i.e. items, users and user-item matching algorithms, various approaches of recommendation systems i...
Mining High Utility Itemsets from its Concise and Lossless Representations
Abstract: Mining high utility items from databases using the utility of items is an emerging technology.Recent algorithms have a drawback in the performance level considering memory and time.Novel strategy proposed here...
Thorny Issues of Stakeholder Identification and Prioritization in Requirement Engineering Process
Identifying the stakeholder in requirement engineering process is one of the critical issues. It performs a remarkable part for successful project completion. The software project largely depends on several  ...
Evolution of Sha-176 Algorithm
To maintain data integrity hash functions are generally used. Hash function is one type of cryptographic primitives, which provide an assurance for data integrity. NAS has designed SHA hash functions which are th...
Role of Computers in Bioinformatics by Using Different Biological Datasets
Abstract: The amount and variety of data in natural sciences increases rapidly. Data abstraction, data manipulation and pattern discovery techniques are of great need in order to deal with such large quantities....