Filters








34,026 Hits in 5.1 sec

Identifying Unclear Questions in Community Question Answering Websites [chapter]

Jan Trienes, Krisztian Balog
2019 Lecture Notes in Computer Science  
We construct a novel dataset and propose a classification approach that is based on the notion of similar questions. This approach is compared to state-of-the-art text classification baselines.  ...  Thousands of complex natural language questions are submitted to community question answering websites on a daily basis, rendering them as one of the most important information sources these days.  ...  This work was partially funded by the University of Twente Tech4People Datagrant project.  ... 
doi:10.1007/978-3-030-15712-8_18 fatcat:owyfo3obpnay5kmfmddheiz7jq

Accelerating instant question search with database techniques

Takeharu Eda, Toshio Uchiyama, Katsuji Bessho, Norifumi Katafuchi, Alice Chen, Ryoji Kataoka
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
A question database is semantically analyzed and searched in the semantic space by boosting the performance of similarity searches with database techniques such as server/client caching and LSH (Locality  ...  This unconscious editing-as-a-sequence-of-searches approach helps users to form their question incrementally through interactive supplementary information.  ...  Figure 8 : 8 Topic Convergence: How the rank of the original question is changed while a user composes the question as a query?  ... 
doi:10.1145/1963192.1963290 dblp:conf/www/EdaUBKCK11 fatcat:k43wwxmbpfe5tm4iax5bmqcoie

Learning to Retrieve Videos by Asking Questions [article]

Avinash Madasu, Junier Oliva, Gedas Bertasius
2022 arXiv   pre-print
The key contribution of our framework is a novel multimodal question generator that learns to ask questions that maximize the subsequent video retrieval performance.  ...  To overcome this limitation, we propose a novel framework for Video Retrieval using Dialog (ViReD), which enables the user to interact with an AI agent via multiple rounds of dialog.  ...  A: No, she doesn't interact with the dog. Q: What is the color of the pajamas? A: The color of the pajamas is red. Rank 98 Rank 37 Rank 9 Rank 385 Rank 48 Rank 7 Q: Is he wearing glasses?  ... 
arXiv:2205.05739v2 fatcat:yg2cpp33vrh3lddmgkwijknhva

Knowledge-Driven Distractor Generation for Cloze-style Multiple Choice Questions [article]

Siyu Ren, Kenny Q. Zhu
2020 arXiv   pre-print
In this paper, we propose a novel configurable framework to automatically generate distractive choices for open-domain cloze-style multiple-choice questions, which incorporates a general-purpose knowledge  ...  base to effectively create a small distractor candidate set, and a feature-rich learning-to-rank model to select distractors that are both plausible and reliable.  ...  However, those methods generally assume prior knowledge of a specific domain (e.g., science) of the given question and then use corresponding domain-specific vocabulary as candidate distractor set, ranked  ... 
arXiv:2004.09853v3 fatcat:rmdmsonfxfcwnd6sl5jy4z6d7y

Adaptable Closed-Domain Question Answering Using Contextualized CNN-Attention Models and Question Expansion

Mahsa Abazari Kia, Aygul Garifullina, Mathias Kern, Jon Chamberlain, Shoaib Jameel
2022 IEEE Access  
In this paper, we present a novel versatile reading comprehension style approach for closed-domain QA (called CA-AcdQA).  ...  In closed-domain Question Answering (QA), the goal is to retrieve answers to questions within a specific domain.  ...  The Hyperopt algorithm utilizes a form of Bayesian optimization and requires the search space, the loss function, the optimization algorithm, and a database for recording hyperparameter tuning history  ... 
doi:10.1109/access.2022.3170466 fatcat:64rbm4tiqfb3hi4law253ioina

System effectiveness, user models, and user utility

Ben Carterette
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
These measures are often formulated as a sum over the product of a discount function of ranks and a gain function mapping relevance assessments to numeric utility values.  ...  Along the way we present a collection of novel results about specific measures and relationships between them.  ...  Any opinions, findings and conclusions or recommendations expressed in this material are the author's and do not necessarily reflect those of the sponsor.  ... 
doi:10.1145/2009916.2010037 dblp:conf/sigir/Carterette11 fatcat:njyximtvwzc5bg5uhigeximdca

Statistical source expansion for question answering

Nico Schlaefer, Jennifer Chu-Carroll, Eric Nyberg, James Fan, Wlodek Zadrozny, David Ferrucci
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
on rankings generated by a web search engine, and 75% when using a multi-document summarization algorithm.  ...  The statistical models use a comprehensive set of features to predict the topicality and quality of text nuggets based on topic models built from seed content, search engine rankings and surface characteristics  ...  In Section 5.3 we perform a detailed analysis of the utility of individual features for the task of ranking text nuggets by relevance.  ... 
doi:10.1145/2063576.2063632 dblp:conf/cikm/SchlaeferCNFZF11 fatcat:whoy62klazctbdo4p57wbevkdu

Complex Knowledge Base Question Answering: A Survey [article]

Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen
2022 arXiv   pre-print
Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions.  ...  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.  ...  [74] proposed a novel ranking model which exploits the structure of query graphs and uses attention weights to explicitly compare predicates with natural language questions.  ... 
arXiv:2108.06688v2 fatcat:frcdrrhbsncm3kprehnz563yfq

Information: a question of quality?

Hans Peter Ohly
2012 Scire. Representación y organización del conocimiento  
Some solution can be given by respecting the different complexities of user types, whereas a combination of all quality approaches is still a demanding task  ...  This paper describes the nature of information and its quality criteria.  ...  Quality is thus not static nor relative, but a question of adaptability to user groups, user needs, and user expectations.  ... 
doi:10.54886/scire.v17i1.4002 fatcat:mm437ahnxnebncxhwsoeqc55f4

A Mobile based Intelligent Question Answering System for Education Domain

Karpagam K, Saradha A
2018 International Journal of Information Engineering and Electronic Business  
In this paper, we present mobile based question answering system acts as a personal assistant in learning and for providing the user with information on computers, software and hardware, book reviews by  ...  The domain of intelligent question answering systems is leading the major role in fulfill the user requirement with specific answers stimulate QA research to the next level with machine learning techniques  ...  This app is novel in that achieves lightweight answer search with the knowledge base and optimizes results using natural inspired algorithm.  ... 
doi:10.5815/ijieeb.2018.01.03 fatcat:apl24ngx2bbl7osc7yznob7xuu

EndCold: An End-to-End Framework for Cold Question Routing in Community Question Answering Services

Jiankai Sun, Jie Zhao, Huan Sun, Srinivasan Parthasarathy
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
We conducted extensive experiments to confirm the usefulness of incorporating the textual information from question tags and demonstrate that an end-2-end framework can achieve promising performances on  ...  Therefore, we propose to address the challenge of leveraging heterogeneous graph and textual information for cold question routing by designing an end-to-end framework that jointly learns CQA node embeddings  ...  Acknowledgments Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/445 dblp:conf/ijcai/Zhao0Y0Z0X20 fatcat:tlus4njwwbfqdne6ifwc7ig3eq

Questions developers ask while diagnosing potential security vulnerabilities with static analysis

Justin Smith, Brittany Johnson, Emerson Murphy-Hill, Bill Chu, Heather Richter Lipford
2015 Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering - ESEC/FSE 2015  
A better understanding of the types of questions asked by developers may help toolsmiths design more effective tools.  ...  We equipped them with Find Security Bugs, a security-oriented static analysis tool, and observed their interactions with security vulnerabilities in an open-source system that they had previously contributed  ...  We presented the results of our study as a categorization of questions. Our findings have several implications for the design of static analysis tools.  ... 
doi:10.1145/2786805.2786812 dblp:conf/sigsoft/SmithJMCL15 fatcat:guvg5fuenzco5dzglmja4ucjmm

Neural Domain Adaptation for Biomedical Question Answering [article]

Georg Wiese, Dirk Weissenborn, Mariana Neves
2017 arXiv   pre-print
Our network architecture is based on a state-of-the-art QA system, extended with biomedical word embeddings and a novel mechanism to answer list questions.  ...  Despite this fact, our systems achieve state-of-the-art results on factoid questions and competitive results on list questions.  ...  Acknowledgments This research was supported by the German Federal Ministry of Education and Research (BMBF) through Software Campus project GeNIE (01IS12050).  ... 
arXiv:1706.03610v2 fatcat:terefio4trhidlwmleusdzow3y

Visual Question Answering: A Tutorial

Damien Teney, Qi Wu, Anton van den Hengel
2017 IEEE Signal Processing Magazine  
A second parallel motivation for the study of VQA is its utility in its own right.  ...  In [71] , the authors propose to retrieve visual information from web searches in the form of exemplar images of question words.  ... 
doi:10.1109/msp.2017.2739826 fatcat:krutfkfw2rcnrmlxvmdp3qcmze

Neural Domain Adaptation for Biomedical Question Answering

Georg Wiese, Dirk Weissenborn, Mariana Neves
2017 Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)  
Our network architecture is based on a state-of-theart QA system, extended with biomedical word embeddings and a novel mechanism to answer list questions.  ...  Despite this fact, our systems achieve state-of-the-art results on factoid questions and competitive results on list questions.  ...  Acknowledgments This research was supported by the German Federal Ministry of Education and Research (BMBF) through Software Campus project GeNIE (01IS12050).  ... 
doi:10.18653/v1/k17-1029 dblp:conf/conll/WieseWN17 fatcat:aig6evwimfczlfxokaytvwnnrq
« Previous Showing results 1 — 15 out of 34,026 results