17,859 Hits in 5.8 sec

Disambiguating named entities with deep supervised learning via crowd labels

Le-kui Zhou, Si-liang Tang, Jun Xiao, Fei Wu, Yue-ting Zhuang
2017 Frontiers of Information Technology & Electronic Engineering  
Named entity disambiguation (NED) is the task of linking mentions of ambiguous entities to their referenced entities in a knowledge base such as Wikipedia.  ...  The learned DCNN is employed to obtain deep crowd features to enhance traditional hand-crafted features for the NED task.  ...  Unlike conventional feature extraction methods, crowd features incorporate human knowledge into machine algorithms.  ... 
doi:10.1631/fitee.1601835 fatcat:jsk7ohle6nezxf46znt6n3ctvi

Knowledge Mining with Scene Text for Fine-Grained Recognition [article]

Hao Wang, Junchao Liao, Tianheng Cheng, Zewen Gao, Hao Liu, Bo Ren, Xiang Bai, Wenyu Liu
2022 arXiv   pre-print
To further validate the effectiveness of the proposed method, we create a new dataset on crowd activity recognition for the evaluation.  ...  Experiments on two benchmark datasets, Con-Text, and Drink Bottle, show that our method outperforms the state-of-the-art by 3.72\% mAP and 5.39\% mAP, respectively.  ...  Acknowledgements This work was supported by the National Natural Science Foundation of China 61733007.  ... 
arXiv:2203.14215v1 fatcat:q7nprbaqqfbjdcyglwq27s5s4i

Crowd-Sensing Meets Situation Awareness: A Research Roadmap for Crisis Management

Andrea Salfinger, Sylva Girtelschmid, Birgit Proll, Werner Retschitzegger, Wieland Schwinger
2015 2015 48th Hawaii International Conference on System Sciences  
This paper makes a first attempt towards this by a reference architecture incorporating crowd-sensed crisis information into SAW systems.  ...  A common understanding about the necessary functionality of such crowd-sensed SAW systems for crisis management, however, is not yet reached nor is a detailed comparison thereof available up to now.  ...  Approaches employing NER mostly focus on extracting location entities, followed by person and organization entities (e. g., in Twitcident).  ... 
doi:10.1109/hicss.2015.28 dblp:conf/hicss/SalfingerGPRS15 fatcat:acrez2mlrbezhmkbjfqvcatw6m

Database Search Results Disambiguation for Task-Oriented Dialog Systems [article]

Kun Qian, Ahmad Beirami, Satwik Kottur, Shahin Shayandeh, Paul Crook, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar
2021 arXiv   pre-print
In this paper, we propose Database Search Result (DSR) Disambiguation, a novel task that focuses on disambiguating database search results, which enhances user experience by allowing them to choose from  ...  For instance, current dialog systems cannot effectively handle multiple search results when querying a database, due to the lack of such scenarios in existing public datasets.  ...  To avoid redundant option lists, we limit the number of options to less than five. The target of the task is to extract the entity of the result selected by the user.  ... 
arXiv:2112.08351v1 fatcat:3iu44wsmeff7dgcpz2xjl23sv4

OntoInfoG++: A Knowledge Fusion Semantic Approach for Infographics Recommendation

Gerard Deepak, Adithya Vibakar, A. Santhanavijayan
2021 International Journal of Interactive Multimedia and Artificial Intelligence  
crowd sourced ontologies to recommend infographics based on the topic of interest of the user.  ...  The semantic alignment is achieved using three distinct measures namely the Horn's index, EnAPMI measure and information entropy.  ...  Acknowledgment The authors thank the Ministry of Human Resources Development, India and the National Institute of Technology, Tiruchirappalli for funding this research by timely release of HTRA Research  ... 
doi:10.9781/ijimai.2021.12.005 fatcat:pjyiovkvwzfcljkvhdwzcqe4k4

Using the Crowd to Improve Search Result Ranking and the Search Experience

Yubin Kim, Kevyn Collins-Thompson, Jaime Teevan
2016 ACM Transactions on Intelligent Systems and Technology  
We then explore ways to incorporate the crowd into the search process that more drastically alter the overall experience.  ...  However, the gains that we observe are limited and unlikely to make up for the extra cost and time that the crowd requires.  ...  CROWD-ENHANCED RANKING Using these three stages as our guide, we begin by looking at conservative approaches to incorporate crowdsourcing into each stage in a way that preserves the overall user experience  ... 
doi:10.1145/2897368 fatcat:symwsreokzcsvg6oko6lzi7h7a

Using microtasks to crowdsource DBpedia entity classification: A study in workflow design

Qiong Bu, Elena Simperl, Sergej Zerr, Yunjia Li, Marta Sabou, Lora Aroyo, Kalina Bontcheva, Alessandro Bozzon
2018 Semantic Web Journal  
We studied three different workflows: an iterative one based on freetext suggestions assessed by the crowd; one that uses an automatic entity typing tool to shortlist ontology classes; and a third one  ...  We discuss these findings and their potential implications for the design of effective crowdsourced entity classification in DBpedia and beyond.  ...  They extracted the entity name, some contextual information, and candidate links from the LOD cloud and published them as microtasks to be assessed by the crowd.  ... 
doi:10.3233/sw-170261 fatcat:ejnyp73w3nhvjke4hzstkkrmjm

Towards the Modelling of Veillance based Citizen Profiling using Knowledge Graphs

Siraj Munir, Syed Imran Jami, Shaukat Wasi
2021 Open Computer Science  
Our contribution is towards enriching the data acquisition process by adding sousveillance mechanism and facilitating semantic queries through representation of Citizen Profiles using Temporal Knowledge  ...  Another improvement can be to incorporate a decentralized version of database for maintaining Citizen profile.  ...  Knowledge of multiple domains need to be incorporated in the system for effective tracking of entities.  ... 
doi:10.1515/comp-2020-0209 fatcat:zay5zfuhkvfdfnzoxe353pjpa4

Learning for Biomedical Information Extraction: Methodological Review of Recent Advances [article]

Feifan Liu, Jinying Chen, Abhyuday Jagannatha, Hong Yu
2016 arXiv   pre-print
Unlike existing reviews covering a holistic view on BioIE, this review focuses on mainly recent advances in learning based approaches, by systematically summarizing them into different aspects of methodological  ...  In addition, we dive into open information extraction and deep learning, two emerging and influential techniques and envision next generation of BioIE.  ...  +mining OR text+processing OR natural+language+processing) AND (information+extraction OR named+entity+detection OR named+entity+recognition OR relation+extraction OR event+extraction)".  ... 
arXiv:1606.07993v1 fatcat:7d5om7zxxzhoviiriasrfwg3xi

AutoTriggER: Named Entity Recognition with Auxiliary Trigger Extraction [article]

Dong-Ho Lee, Ravi Kiran Selvam, Sheikh Muhammad Sarwar, Bill Yuchen Lin, Mahak Agarwal, Fred Morstatter, Jay Pujara, Elizabeth Boschee, James Allan, Xiang Ren
2021 arXiv   pre-print
Deep neural models for low-resource named entity recognition (NER) have shown impressive results by leveraging distant super-vision or other meta-level information (e.g. explanation).  ...  Thus, the framework is able to both create and leverage auxiliary supervision by itself.  ...  For BC5CDR and CoNLL03, we also have crowd- Table 2 : 2 Performance comparison (F1-score) of named entity recognition on BC5CDR, JNLPBA, and CoNLL03 datasets by different percentage usage of the train  ... 
arXiv:2109.04726v2 fatcat:6fmnnlmrhjbgbfjilmihew4qpe

A study of similar question retrieval method in online health communities

Bufei Xing, Haonan Yin, Zhijun Yan, Jiachen Wang
2021 International Journal of Crowd Science  
Originality/value This method conquers the problem of word mismatch and considers the named entities included in questions, which most of existing studies did not.  ...  The domain knowledge similarity can evaluate the domain distance between different questions. And the topic similarity measures questions' relationship base on the extracted latent topics.  ...  The method this study adopts is the widely used named entity extraction method. In future work, we plan to improve the named entity extraction performance to enhance our method.  ... 
doi:10.1108/ijcs-03-2021-0006 fatcat:4yjkeke4gnhv3pmqv6b7qgho4m

An extended study of content and crowdsourcing-related performance factors in named entity annotation

Oluwaseyi Feyisetan, Elena Simperl, Markus Luczak-Roesch, Ramine Tinati, Nigel Shadbolt, Marta Sabou, Lora Aroyo, Kalina Bontcheva, Alessandro Bozzon
2018 Semantic Web Journal  
Hybrid annotation techniques have emerged as a promising approach to carry out named entity recognition on noisy microposts.  ...  Our findings show that crowd workers correctly annotate shorter tweets with fewer entities, while they skip (or wrongly annotate) longer tweets with more entities.  ...  Implicitly named entities In our investigation we paid special attention to those entities that were annotated by the crowd but that were not covered by the gold standard.  ... 
doi:10.3233/sw-170282 fatcat:ibzxiiixubddxhl5xnoiyb275e


P. Gokulakrishnan, D. Suresh, S. Satheesbabu
2021 Information Technology in Industry  
The goal of this work is to enhance the crowd-sourcing classification task efficiency with Dynamic Resource Algorithm.  ...  The software of classification tasks in crowd-sourcing is a counter step due to the inclined reputation of crowd-sourcing market.  ...  B.FEATURE EXTRACTION Feature Extraction can be done by C4.5 (J48) Algorithm, Which defines the product added by the admin, is belonging to Electronics or Appliances or Accessories, etc.  ... 
doi:10.17762/itii.v9i1.246 fatcat:stwq4od7a5alhm7atigjygjsju

Neural relation extraction: a survey [article]

Mehmet Aydar and Ozge Bozal and Furkan Ozbay
2020 arXiv   pre-print
Neural relation extraction discovers semantic relations between entities from unstructured text using deep learning methods.  ...  In this study, we present a comprehensive review of methods on neural network based relation extraction.  ...  [59] investigate the effect of incorporating adversarial training in relation extraction.  ... 
arXiv:2007.04247v1 fatcat:xxrcy2ef75dk5aeijqlf6tjgke

Cross-media Event Extraction and Recommendation

Di Lu, Clare Voss, Fangbo Tao, Xiang Ren, Rachel Guan, Rostyslav Korolov, Tongtao Zhang, Dongang Wang, Hongzhi Li, Taylor Cassidy, Heng Ji, Shih-fu Chang (+5 others)
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations  
In this paper we briefly present the algorithms of each component and demonstrate the system's capabilities 1 .  ...  The sheer volume of unstructured multimedia data (e.g., texts, images, videos) posted on the Web during events of general interest is overwhelming and difficult to distill if seeking information relevant  ...  Acknowledgments This work was supported by the U.S. ARL NS-CTA No. W911NF-09-2-0053, DARPA Multimedia Seedling grant, DARPA DEFT No. FA8750-13-2-0041 and NSF CAREER Award IIS-1523198.  ... 
doi:10.18653/v1/n16-3015 dblp:conf/naacl/LuVTRGKZWLCJCHW16 fatcat:kxehxhclqzacpa6rtxijgqgsqy
« Previous Showing results 1 — 15 out of 17,859 results