24,490 Hits in 6.2 sec

Distractor Generation for Multiple Choice Questions Using Learning to Rank

Chen Liang, Xiao Yang, Neisarg Dave, Drew Wham, Bart Pursel, C Lee Giles
2018 Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications  
We investigate how machine learning models, specifically ranking models, can be used to select useful distractors for multiple choice questions.  ...  These two datasets can also be used as benchmarks for distractor generation.  ...  Acknowledgments We gratefully acknowledge partial support from the Pennsylvania State University Center for Online Innovation in Learning and helpful comments from the reviewers.  ... 
doi:10.18653/v1/w18-0533 dblp:conf/bea/LiangYDWPG18 fatcat:tlamiu4k65f6teknugncrcxf2u

First-principle study on honeycomb fluorated-InTe monolayer with large Rashba spin splitting and direct bandgap

Kaixuan Li, Xiujuan Xian, Jiafu Wang, Niannian Yu
2019 Applied Surface Science  
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques  ...  Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this  ...  Based on the thorough analysis of recent work, we give the specific definition of MRC tasks and compare them with each other in depth.  ... 
doi:10.1016/j.apsusc.2018.11.214 fatcat:dg2eusl7ufhttcsqlllyiisxb4

Neural Machine Reading Comprehension: Methods and Trends

Shanshan Liu, Xin Zhang, Sheng Zhang, Hui Wang, Weiming Zhang
2019 Applied Sciences  
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques  ...  Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this  ...  As a multiple-choice task, RACE asks for more reasoning, because questions and answers are human-generated and simple methods based on information retrieval or word co-occurrence may not perform well.  ... 
doi:10.3390/app9183698 fatcat:bpwwfikrpvh4dhphyl3ezpnn5e

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations [article]

Qian Li, Hao Peng, Jianxin Li, Jia Wu, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
2021 arXiv   pre-print
To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process.  ...  While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches.  ...  We thank the anonymous reviewers for their insightful reported question answering based method MQAEE [20] on comments and suggestions.  ... 
arXiv:2106.12384v2 fatcat:blyylym77vdupbrolil2dtmrna

A Survey on Legal Question Answering Systems [article]

Jorge Martinez-Gil
2021 arXiv   pre-print
This is mainly because a Question Answering system could be able to automatically process a massive amount of legal resources to answer a question or doubt in seconds, which means that it could save resources  ...  The two main reasons for this are that most legislation is usually unstructured, and the tremendous amount and pace with which laws are released causes information overload in their daily tasks.  ...  Acknowledgments This research work has been partially supported by the Austrian Ministry for Transport, Innovation and Technology, the Federal Ministry of Science, Research and Economy, and the Province  ... 
arXiv:2110.07333v1 fatcat:a3pgndtdrnemxortichxztfaoy

Question Recommendation Mechanism under Q&A Community based on LDA Model

Caiyin Wang, Lin Cui, Baosheng Yang, Xiaoyin Wu
2014 Open Cybernetics and Systemics Journal  
Aiming at the questions not answered timely under Q&A community, a kind of questions recommendation method based on LDA (Latent Dirichlet Allocation) topic model is proposed, which fully utilizes personalized  ...  Experimental results show that the proposed questions recommendation method based on LDA not only discoveries the unsolved questions quickly, but also recommends the most suitable answers to users compared  ...  Bian et al. proposed a semi-supervised mutually reinforcing framework computing content quality and user reputation under Q&A community [5] .  ... 
doi:10.2174/1874110x01408010645 fatcat:3wqwkiqxuzg45bidwpvgiozhy4

Pre-training Text-to-Text Transformers for Concept-centric Common Sense [article]

Wangchunshu Zhou, Dong-Ho Lee, Ravi Kiran Selvam, Seyeon Lee, Bill Yuchen Lin, Xiang Ren
2020 arXiv   pre-print
Furthermore, we develop a joint pre-training framework to unify generative and contrastive objectives so that they can mutually reinforce each other.  ...  suggests that CALM can serve as a general, plug-and-play method for improving the commonsense reasoning ability of a PTLM.  ...  . , x n ], we first conduct part-of-speech tagging for the sentence and extract Verb, Noun, and Proper Nouns from the sentence to use as concepts 2 .  ... 
arXiv:2011.07956v2 fatcat:q32hm5y4pndvjfitx6757pxywy

On-line and Memory-based: Revisiting the Relationship Between Candidate Evaluation Processing Models

Young Mie Kim, Kelly Garrett
2011 Political Behavior  
Reexamining the relationship between the on-line and memory-based information processing models, this study presents a theoretical basis for the co-occurrence of on-line and memory-based processes and  ...  Keywords Hybrid model Á On-line information processing Á Memory-based information processing Á Candidate evaluation Á Vote choice Á Presidential election debate Scholarly perspectives on information processing  ...  Acknowledgment We would like to thank Prabu David for his support for data collection.  ... 
doi:10.1007/s11109-011-9158-9 fatcat:vmuatug5czehxa4nzh57qkxhua

Information: Theory, brain, and behavior

Greg Jensen, Ryan D. Ward, Peter D. Balsam
2013 Journal of The Experimental Analysis of Behavior  
Moreover, how can this information be extracted and these computations be made "on the fly," as they so often must be?  ...  At any given moment, the brain continuously processes imperfect signals from a noisy world, and initiates and channels activity given the available information, doing so in a distributed fashion.  ...  dictates what an organism learns, or merely their co-occurrence.  ... 
doi:10.1002/jeab.49 pmid:24122456 pmcid:PMC5226236 fatcat:cg2lah2l7fcczgxjdkud66hexi

How value co-creation and co-destruction unfolds: a longitudinal perspective on dialogic engagement in health services interactions

Debbie Isobel Keeling, Kathleen Keeling, Ko de Ruyter, Angus Laing
2020 Journal of the Academy of Marketing Science  
We develop and empirically support six dialogic co-creation and co-destruction mechanisms that impact on the resolution of tensions and integration of knowledge resources between service providers and  ...  Taking healthcare as an exemplar, we offer a research agenda for developing our understanding of DE in complex services.  ...  "buy-in" and ownership from the consumer and a strong relationship between professional and consumer based on mutual respect.  ... 
doi:10.1007/s11747-020-00737-z fatcat:nkgko67i7fgqhimbn7z3ddre5y

Topic 7: Japanese Macaque Society as a Complex Adaptive System [chapter]

Nobuyuki Kutsukake
2010 The Japanese Macaques  
Valuable relationships, which are characterized at the level of social interaction by frequent association, proximity, co-feeding, and grooming, are not distributed randomly within a group, but are clearly  ...  dependent on the sex combination of dyads.  ...  Acknowledgments This study was supported by the Hayama Center for Advanced Studies at the  ... 
doi:10.1007/978-4-431-53886-8_19 fatcat:tebmotmaq5aotht7ozzk4juzoq

Integrated Cognitive Architecture for Robot Learning of Action and Language

Kazuki Miyazawa, Takato Horii, Tatsuya Aoki, Takayuki Nagai
2019 Frontiers in Robotics and AI  
The integration of reinforcement learning and mMLDA enables actions based on understanding.  ...  In this paper, we propose a framework for the simultaneously comprehension of concepts, actions, and language as a first step toward this goal.  ...  and TN developed the theory. KM implemented the system and conducted the experiment. KM wrote the manuscript with support from TN, TH, and TA.  ... 
doi:10.3389/frobt.2019.00131 pmid:33501146 pmcid:PMC7805838 fatcat:w4yi262cgbgbjees4evcmzwg5m

Ranking related entities

Marc Bron, Krisztian Balog, Maarten de Rijke
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
We propose a framework for addressing this task and perform a detailed analysis of four core components; co-occurrence models, type filtering, context modeling and homepage finding.  ...  To correct for (2), we add contextual information, represented as language models derived from documents in which source and target entities co-occur.  ...  This pipeline resembles a question answering architecture, where first candidate answers are generated, followed by type filtering and the final ranking (scoring) steps.  ... 
doi:10.1145/1871437.1871574 dblp:conf/cikm/BronBR10 fatcat:3a3kgjmwezhxpksi7v5s2p4xl4

Establishing how social capital is studied in relation to cardiovascular disease and identifying gaps for future research—A scoping review protocol

Marie Parker, Xiangming Fang, Shannon Renee Self-Brown, Ali Rahimi, Bart Ferket
2021 PLoS ONE  
Discussion The synthesis of this evidence base is intended to provide a framework for how social capital has been defined and measured in the cardiovascular literature, with additional guidance for future  ...  and (2) What gaps exist in the evaluation of the relationship between social capital and cardiovascular disease? Materials and methods A scoping review will be used to answer the research questions.  ...  co-occurrence trends.  ... 
doi:10.1371/journal.pone.0249751 pmid:33831051 fatcat:i2yzs2mhkva7dcr5kytfcaw4ne

Bridging the Vocabulary Gap between Health Seekers and Healthcare Knowledge

Liqiang Nie, Yi-Liang Zhao, Mohammad Akbari, Jialie Shen, Tat-Seng Chua
2015 IEEE Transactions on Knowledge and Data Engineering  
To bridge this gap, this paper presents a novel scheme to code the medical records by jointly utilizing local mining and global learning approaches, which are tightly linked and mutually reinforced.  ...  A corpus-aware terminology vocabulary is naturally constructed as a byproduct, which is used as the terminology space for global learning.  ...  To be specific, given a medical record with locally mined terminologies, an ordered list of m terminology candidates were derived for each of the locally mined terminologies based on the their co-occurrences  ... 
doi:10.1109/tkde.2014.2330813 fatcat:u7mtdhsb65fwlhh254ql45dkeu
« Previous Showing results 1 — 15 out of 24,490 results