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 76
- Downloads 0
Intelligent Fault Identification System for Transmission Lines Using Artificial Neural Network
Transmission and distribution lines are vital links between generating units and consumers. They are exposed to atmosphere, hence chances of occurrence of fault in transmission line is very high, which has to be...
Lip Recognition for Authentication and Security
Abstract: Lip is used as an identifier from person to person as the size of the upper and lower lips, furrows, grooves, the distances between the lines and the edges vary individualistically. These unique parameter...
A Survey on Data Annotation for the Web Databases
Abstract : Web search engines are designed to search information in the web database and to return dynamic web pages. Data unit’s returns from the databases and information technology are accessible through HTML fo...
ID3 Derived Fuzzy Rules for Predicting the Students AcedemicPerformance
Abstract: This paper presents a technique to use ID3 decision rules to produce fuzzy rules to get the optimizeprediction of the students academic performance. In this paper, a the student administrative data for a...
Segmentation to Sound Conversion
Abstract: Our motive, the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech, our approach does not r...