A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Asking Easy Questions: A User-Friendly Approach to Active Reward Learning
[article]
2019
arXiv
pre-print
Simulations and a user study show our method not only produces easy questions, but also ultimately results in faster reward learning. ...
Robots can learn the right reward function by querying a human expert. ...
Toyota Research Institute (TRI) provided funds to assist the authors with their research but this article solely reflects the opinions and conclusions of its authors and not TRI or any other Toyota entity ...
arXiv:1910.04365v1
fatcat:53wiv6e5rjd2lpb2gqwk6alomi
Here's What I've Learned: Asking Questions that Reveal Reward Learning
[article]
2021
arXiv
pre-print
Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. ...
We develop and test a model that robots can leverage to relate the questions they ask to the information these questions reveal. ...
USER STUDIES We conducted two in-person user studies to compare our approach to a state-of-the-art active learning baseline. ...
arXiv:2107.01995v1
fatcat:rmz5nq2upnfj3ijx326xnggde4
Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
[article]
2021
arXiv
pre-print
In addition, we build a goal-oriented visual dialogue task called CLEVR Ask. It synthesizes complex scenes that require the Questioner to generate descriptive questions. ...
In particular, goal-oriented visual dialogue, where the aim of the agent is to seek information by asking questions during a turn-taking dialogue, has been gaining scholarly attention recently. ...
For example, in simple scenes, where each object has different attributes and thus is easy to distinguish, the Questioner only needs to ask category-based questions such as "Is it a car?". ...
arXiv:2106.15550v1
fatcat:6t6mync2dzdqrpd4vb36selr7m
Open-Domain Question Answering with Pre-Constructed Question Spaces
[article]
2020
arXiv
pre-print
user queries by searching the pre-constructed question spaces for answers that are most likely to be asked in the given way. ...
Open-domain question answering aims at solving the task of locating the answers to user-generated questions in massive collections of documents. ...
When users enter queries online, a retriever compares user queries with the pre-constructed question spaces to retrieve the answers that are most likely to be asked in the given way. ...
arXiv:2006.08337v2
fatcat:e26hfba5evcfjfrdbbhysyafiy
Why Answer this Question? Experts' Behaviors on Educational Community Question-Answering Platforms
2022
Electronic Journal of e-Learning
answer was mainly set by their motives to make a difference for the learner and partially by the user-friendliness of the platform (added value of answering and CQA platform's usability); and finally, ...
We examined experts' perceptions of three dimensions: the CQA platform's usability, the quality of questions asked, and the added value of answering these questions. ...
with. .874 It is easy for me to handle my settings on the 100mentors app. .855 It is easy for me to find help/assistance for the use of the 100mentors app. .833 It is easy for me to select suitable questions ...
doi:10.34190/ejel.20.2.2240
fatcat:auqpz27iobenvhj73x3gt2qvzi
Proposal for Using NLP Interchange Format for Question Answering in Organizations
2013
International Web Rule Symposium
Natural language processing technique is mostly implemented in QA system for asking user"s question and several steps are also followed for conversion of questions to query form for getting an exact answer ...
Different methods for user-friendly knowledge access have been developed previously. ...
This support (2009SGR 1365) was granted to the Knowledge Engineering & Machine Learning group (KEMLG). ...
dblp:conf/ruleml/Latifi13
fatcat:h447vnbwfvh5ppbb6fykg72shy
Questions & Answers & Tweets
2011
Social Science Research Network
It is an attempt to use the internet to make television better rather than to concede its eclipse, by marrying brief fragments of online speech with the one-way, single-channel authority of a television ...
Q&A integrates broadcast and online content in a way the program makers thought would serve the animating purpose of the television program: to increase public engagement in politics. ...
to ask the question they submitted in advance. ...
doi:10.2139/ssrn.2017330
fatcat:c3bdjeulyvat3egcxhuxf42xt4
It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books
[article]
2022
arXiv
pre-print
Existing question answering (QA) techniques are created mainly to answer questions asked by humans. ...
But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. ...
In fact, a couple of recent works use this dataset and train a network by combining a QG module and a QA module with a reinforcement learning approach (Tang et al., 2017) . ...
arXiv:2109.03423v4
fatcat:sp5sqw2dtnd4voambk54u6qli4
Complex Knowledge Base Question Answering: A Survey
[article]
2022
arXiv
pre-print
Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. ...
Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. ...
As users typically ask followup questions to explore a topic, deployed models are supposed to handle KBQA task in a conversational manner. ...
arXiv:2108.06688v2
fatcat:frcdrrhbsncm3kprehnz563yfq
Evaluation and improvement of student's question-posing ability in a web-based learning environment
2011
Australasian Journal of Educational Technology
To remedy this problem, the present study developed a system of integrating a reward mechanism into assessment activities, to measure the question-posing ability of individual students in a web-based learning ...
However, this learning approach has some difficulties, one being the lack of a practical approach to assist teachers in evaluating the question-posing ability of all learners. ...
The problem might be improved by providing a more user friendly interface and more rewards as incentives. ...
doi:10.14742/ajet.939
fatcat:eetclaadova35efcmbjmdstkwq
A Survey on Expert Recommendation in Community Question Answering
[article]
2018
arXiv
pre-print
Instead of passively waiting for users to browse and find their questions of interest, an expert recommendation method raises the attention of users to the appropriate questions actively and promptly. ...
Community question answering (CQA) represents the type of Web applications where people can exchange knowledge via asking and answering questions. ...
In contrast, language models use a generative approach to compute the wordbased relevance of a user's previous activities to the given question, and in turn, to predict the possibility of a user answering ...
arXiv:1807.05540v1
fatcat:ezque3rbwnex5gvt2u6sbjqsnu
A Survey on Expert Recommendation in Community Question Answering
2018
Journal of Computer Science and Technology
Instead of passively waiting for users to browse and find their questions of interest, an expert recommendation method raises the attention of users to the appropriate questions actively and promptly. ...
Community question answering (CQA) represents the type of Web applications where people can exchange knowledge via asking and answering questions. ...
In contrast, language models use a generative approach to compute the wordbased relevance of a user's previous activities to the given question, and in turn, to predict the possibility of a user answering ...
doi:10.1007/s11390-018-1845-0
fatcat:zedffohznfeqxetyodegdj2gpi
Question-Answer Cards for an Inclusive Micro-tasking Framework for the Elderly
[chapter]
2013
Lecture Notes in Computer Science
We have devised a question-answer card interface to allow the elderly to participate in micro-tasks with minimal ICT skills and learning efforts. ...
The primary target users involve senior citizens who have ICT devices such as smartphones or PCs but who do not actively use such technologies, who appear to be the majority of the senior population, at ...
For the question asking about the compensation, the majority of the senior participants were less concerned about the rewards. The young participants tended to want 5 to 10 yen per card. ...
doi:10.1007/978-3-642-40477-1_38
fatcat:icytgrttjfegnocnmceoww2rbu
Student questioning: A componential analysis
1994
Learning and Individual Differences
Questioning is depicted from start to finish, from the onset of perplexity until the learning that may result. ...
Within this framework a variety of aspects of questioning are highlighted. One focus of the article is individual differences in question asking. ...
The formulation problem is also widely recognized in the computer industry where various attempts have been made to create user-friendly point and query devices to alleviate it (e.g., Lang, Graesser, ...
doi:10.1016/1041-6080(94)90007-8
fatcat:efhspqca7na5pdf6sryb5d2rty
Any questions? Just Ask: Changing library roles at the University of Huddersfield to support widening participation
2009
Library and Information Research
Through developing a more proactive and welcoming approach to supporting students when they entered the Library, it was hoped the Library would be able to contribute to the University's mission to attract ...
This article describes an innovative scheme to improve students' abilities and confidence in using a University library, by adapting the role of library assistants. ...
approach, in which staff would wait meekly for students to ask questions. ...
doi:10.29173/lirg173
fatcat:gkgsvgn5szffhbwispvnp4v7gu
« Previous
Showing results 1 — 15 out of 24,004 results