Proceedings ArticleDOI
Answer Selection In Community Question Answering Portals
Juee Gosavi,B. N. Jagdale +1 more
TLDR
The objective is to rank answer candidates based on pair wise comparison where question-answer pairs are ranked using pair wise learning to a rank approach based on a trained model which provides the user with most relevant answers for a given posted question.Abstract:
New level of information sharing is enabled by different online communities like wikis, blogs, forums etc. which provides a platform for interaction with individuals which offers services like searching and posting queries or answers and share expertise with other information seekers. For recently posted query or searched query system furnishes the pool of answers with similar questions links, which could be a prolonged task for finding the significant answer. To overcome this, the system proposes an approach to effectively rank answers which are most relevant and best from historical archives based on similar queries found. It comprises of two components, one which contains training samples with positive, negative and neutral classes and other component retrieves similar questions to posted questions which are with their answer pools. Two data mining approaches were compared to retrieve similar questions. Our objective is to rank answer candidates based on pair wise comparison where question-answer pairs are ranked using pair wise learning to a rank approach based on a trained model which provides the user with most relevant answers for a given posted question.read more
Citations
More filters
Journal ArticleDOI
Integrated Question-Answering System for Natural Disaster Domains Based on Social Media Messages Posted at the Time of Disaster
TL;DR: The framework of a question-answering (QA) system that was developed using a Twitter dataset containing more than nine million tweets compiled during the Osaka North Earthquake that occurred on 18 June 2018 is presented.
Journal ArticleDOI
Automatic Question Paper Generation using ML: A Review
TL;DR: This framework is developed which is able to make the programmed address paper and this it can be valuable to numerous instructive establishing.
References
More filters
Proceedings ArticleDOI
CQArank: jointly model topics and expertise in community question answering
TL;DR: This work proposed Topic Expertise Model (TEM), a novel probabilistic generative model with GMM hybrid, to jointly model topics and expertise by integrating textual content model and link structure analysis, and proposed CQARank to measure user interests and expertise score under different topics.
Journal ArticleDOI
Disease Inference from Health-Related Questions via Sparse Deep Learning
TL;DR: This paper reports a user study on the information needs of health seekers in terms of questions and proposes a novel deep learning scheme to infer the possible diseases given the questions, which well fits specific tasks with fine-tuning.
Proceedings ArticleDOI
Question-answer topic model for question retrieval in community question answering
TL;DR: A novel Question-Answer Topic Model (QATM) is proposed to learn the latent topics aligned across the question-answer pairs to alleviate the lexical gap problem, with the assumption that a question and its paired answer share the same topic distribution.
Journal ArticleDOI
User Preference Learning for Online Social Recommendation
TL;DR: This paper presents a new framework of online social recommendation from the viewpoint of online graph regularized user preference learning (OGRPL), which incorporates both collaborative user-item relationship as well as item content features into an unified preference learning process and develops an efficient iterative procedure, OGRPL-FW, to solve the proposed online optimization problem.
Proceedings ArticleDOI
Exploiting user feedback to learn to rank answers in q&a forums: a case study with stack overflow
TL;DR: The authors' L2R method was trained to learn the answer rating, based on the feedback users give to answers in Q&A forums, and was able to outperform a state of the art baseline with gains of up to 21% in NDCG, a metric used to evaluate rankings.