Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








12,196 Hits in 5.1 sec

An Oracle-based co-training framework for writer identification in offline handwriting

Utkarsh Porwal, Sreeranga Rajan, Venu Govindaraju, Christian Viard-Gaudin, Richard Zanibbi
2012 Document Recognition and Retrieval XIX  
Traditional forensic document analysis methods have focused on feature-classification paradigm where a machine learning based classifier is used to learn discrimination among multiple writers.  ...  Two learners are initially trained on different views of a smaller labeled training data and their initial hypothesis is used to predict labels on larger unlabeled dataset.  ...  Co-training has been successfully used for semi supervised learning in different areas but never been used for labeling data for writer identification to the best of our knowledge.  ... 
doi:10.1117/12.912221 dblp:conf/drr/PorwalRG12 fatcat:lwiwe74aejd4pcwfkebrh4etxy

Semi-supervised Feature Learning For Improving Writer Identification [article]

Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, Zehong Cao
2018 arXiv   pre-print
Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors.  ...  In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously  ...  Conclusion In this paper, we proposed a semi-supervised feature learning pipeline for offline writer identification.  ... 
arXiv:1807.05490v3 fatcat:dfxtdkumiffetbtpoye4jp35te

A Dynamic Active Safe Semi-Supervised Learning Framework for Fault Identification in Labeled Expensive Chemical Processes

Xuqing Jia, Wende Tian, Chuankun Li, Xia Yang, Zhongjun Luo, Hui Wang
2020 Processes  
A novel active semi-supervised learning framework using unlabeled data is proposed for fault identification in labeled expensive chemical processes.  ...  Finally, a PCA-dynamic active safe semi-supervised support vector machine (PCA-DAS4VM) for fault identification in labeled expensive chemical processes is built.  ...  The semi-supervised learning method has been applied to various fields, such as writer identification [10] , sentiment classification [11] , medical image analysis [12] , traffic flow [13] , etc.  ... 
doi:10.3390/pr8010105 fatcat:vixxiucswba6tpklx24wmouseu

REVIEW OF OFFLINE TEXT INDEPENDENT WRITER IDENTIFICATION TECHNIQUES

Shehzad Khalid, Uzma Naqv, Sana Shokat
2016 Jurnal Teknologi  
Application of writer identification in different language domains is also discussed. Future directions for the automated writer identification are presented in the end.  ...  Classification approaches that are mainly used for identification by the researchers and verification by different groups and individuals are presented.  ...  To exploit the information in the unlabeled data where the writer is unknown a semi supervised structural learning framework presented in [15] that used the multitask learning to provide low dimensional  ... 
doi:10.11113/jt.v78.8252 fatcat:cq3yqawmijcm3kqbagd7h6cg3u

CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web [article]

Colin Lockard, Xin Luna Dong, Arash Einolghozati, Prashant Shiralkar
2018 arXiv   pre-print
In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision.  ...  The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases.  ...  Here we focus on techniques applicable to the semi-structured Web: Wrapper induction: Early work for extracting semi-structured data was based on a supervised learning scheme called wrapper induction  ... 
arXiv:1804.04635v1 fatcat:7g34nyfxvzea5e5zn3j7ejknjm

CERES

Colin Lockard, Xin Luna Dong, Arash Einolghozati, Prashant Shiralkar
2018 Proceedings of the VLDB Endowment  
In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision.  ...  The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases.  ...  Wrapper induction: Early work for extracting semi-structured data was based on a supervised learning scheme called wrapper induction [21, 36, 17, 27] .  ... 
doi:10.14778/3231751.3231758 fatcat:fb4vutdhjfegdapdhd6vrxmhhq

SELF-SUPERVISED ADAPTATION FOR ON-LINE SCRIPT TEXT RECOGNITION [chapter]

Lionel Prevost, Loїc Oudot
2009 Series in Machine Perception and Artificial Intelligence  
The classification expert can be iteratively modified in order to learn the particularities of a writer.  ...  We present in this paper several strategies to adapt this recognizer in a self-supervised way to a given writer and compare them to the supervised adaptation scheme.  ...  Thanks to their structure, they can learn new writings styles, by activating new prototypes and inactivating erroneous ones.  ... 
doi:10.1142/9789812834461_0010 dblp:series/smpai/PrevostO09 fatcat:z4va2hrmlfhylitkcanxmwdzqy

Sarcasm Detection: A Comparative Study [article]

Hamed Yaghoobian, Hamid R. Arabnia, Khaled Rasheed
2021 arXiv   pre-print
Thus far, three main paradigm shifts have occurred in the way researchers have approached this task: 1) semi-supervised pattern extraction to identify implicit sentiment, 2) use of hashtag-based supervision  ...  However, the figurative and creative nature of sarcasm poses a great challenge for affective computing systems performing sentiment analysis.  ...  Learning-based methods In the following, we delve more into supervised learning, semi-supervised learning, unsupervised learning, structural and hybrid learning.  ... 
arXiv:2107.02276v2 fatcat:2tgpyhchbngpnnhj3sezmj4hle

Spam Reviews Detection in the Time of COVID-19 Pandemic: Background, Definitions, Methods and Literature Analysis

Ala' M. Al-Zoubi, Antonio M. Mora, Hossam Faris
2022 Applied Sciences  
Reading and posting online reviews becomes an important part of discussion and decision-making, especially for individuals and organizations.  ...  The study addresses all the spam reviews detection studies for the years 2020 and 2021. In other words, we analyze and examine all works presented during the COVID-19 situation.  ...  Another recent framework proposed by [134] for spam reviews detection using semi-supervised learning.  ... 
doi:10.3390/app12073634 fatcat:bz2emxqkkbaavn5u2nbztfhqle

Open

Colin Lockard, Prashant Shiralkar, Xin Luna Dong
2019 Proceedings of the 2019 Conference of the North  
Given a semi-structured website and a set of seed facts for some relations existing on its pages, we employ a semi-supervised label propagation technique to automatically create training data for the relations  ...  We then use this training data to learn a classifier for relation extraction. Experimental results of this method on our new benchmark dataset obtained a precision of over 70%.  ...  Acknowledgments We wish to thank Hannaneh Hajishirzi for helpful advice, Paolo Merialdo and Valter Crescenzi for help in running WEIR, and Andrew Bridges, Marc Landers, and Alexander Macdonald for their  ... 
doi:10.18653/v1/n19-1309 dblp:conf/naacl/LockardSD19 fatcat:t2m67vij2nhv7f34rk6n5kh5ra

Historical Document Dating Using Unsupervised Attribute Learning

Sheng He, Petros Samara, Jan Burgers, Lambert Schomaker
2016 2016 12th IAPR Workshop on Document Analysis Systems (DAS)  
Non-semantic attributes are discovered in the low-level feature space using an unsupervised attribute learning method.  ...  The date of historical documents is an important metadata for scholars using them, as they need to know the historical context of the documents.  ...  ACKNOWLEDGMENTS This work has been supported by the Dutch Organization for Scientific Research NWO (project No. 380-50-006).  ... 
doi:10.1109/das.2016.38 dblp:conf/das/HeSBS16 fatcat:wgg6nb57zrdldb6iwq7vjctp6y

Structured entity identification and document categorization

Indrajit Bhattacharya, Shantanu Godbole, Sachindra Joshi
2008 Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD 08  
In this paper, we propose a probabilistic generative model for joint entity identification and document categorization.  ...  Using extensive experiments over real and semi-synthetic data, we demonstrate that the two tasks can benefit immensely from each other when performed jointly using the proposed model.  ...  Semi-supervised methods are the most popular among approaches that bootstrap learning on insufficient labeled data by exploiting abundance of unlabeled data [16] .  ... 
doi:10.1145/1401890.1401899 dblp:conf/kdd/BhattacharyaGJ08 fatcat:qw2cdom2p5grjngs6vg6ne5hs4

A Thresholded Gabor-CNN Based Writer Identification System for Indic Scripts

M. F. Mridha, Abu Quwsar Ohi, Jungpil Shin, Muhammad Mohsin Kabir, Muhammad Mostafa Monowar, Md. Abdul Hamid
2021 IEEE Access  
This paper introduces a supervised offline Indic script writer identification system that can identify individuals using less than a single page of handwriting.  ...  For the experiment, we used BanglaWriting dataset, which is openly available for Bengali writing and writer recognition. Further, we added Devanagari and Telugu datasets for evaluation.  ...  ACKNOWLEDGMENT The authors would like to thank the Advanced Machine Learning (AML) lab for resource sharing and precious opinions.  ... 
doi:10.1109/access.2021.3114799 fatcat:4ktqpgrl6fa6pcjmequfku7rpq

A PANOPTICS OF SENTIMENTAL ANALYSIS

K. Venkata Raju
2017 International Journal of Advanced Research in Computer Science  
In this paper we present a comprehensive review of model and recent trend of research used in implementation of sentimental analysis.  ...  Nowadays decision making is very much impacted by the products and services reviews of the products/item, these review data can be used to define trends over time.  ...  Sarcasm is a classy type act of speech in which the speakers/writers says contradictory meaning, sarcasms are identified by semi-supervised learning method.  ... 
doi:10.26483/ijarcs.v8i7.4448 fatcat:o5anrkuknvdzfdn6275zdeyrsa

A Novel Integrated Framework for Sarcasm Detection In Social Platform

2020 International Journal of Engineering and Advanced Technology  
This paper also introduces a novel integrated framework for identifying sarcastic clues in tweets, and recognizing sarcastic users.  ...  Sarcasm identification in social media is a crucial facet of the sentiment analysis process, since it deals with texts whose polarity is completely opposite from its utterance.  ...  [13] demonstrated a semi-supervised learning algorithm, for recognizing sarcasm that exploits both syntactic and pattern-based feature extraction.  ... 
doi:10.35940/ijeat.d7519.049420 fatcat:cnstgqhnkbhmndhcenmbu5jp24
« Previous Showing results 1 — 15 out of 12,196 results