Filters








115,491 Hits in 6.4 sec

Acquiring Word Similarities with Higher Order Association Mining [chapter]

Sutanu Chakraborti, Nirmalie Wiratunga, Robert Lothian, Stuart Watt
Lecture Notes in Computer Science  
If word A co-occurs with word B, we say A and B share a first order association between them.  ...  In this paper we present algorithms for mining higher order co-occurrences. A weighted linear model is used to combine the contribution of these higher orders into a word similarity model.  ...  Section 3 explains the concept of higher order associations, along with algorithms to mine the same. Section 4 describes our model of word similarities.  ... 
doi:10.1007/978-3-540-74141-1_5 fatcat:uzuxnorj2rb7lfpbky3dr4gyge

The HWS hybrid web search

Lixin Han, Guihai Chen
2006 Information and Software Technology  
In this paper, we propose a hybrid web search architecture-HWS, which combines text search with semantic search to improve precision and recall.  ...  The RK algorithm is described below: Input: text corpus, keywords, minimum support Effect: association words { the frequencies of the words is counted and ordered by a single word; the words with higher  ...  frequencies such as preposition, article, or conjunction are deleted; countZn; // n is the total number of words with higher frequencies CZnil; associationZ{ n words with higher frequencie }; While countS1  ... 
doi:10.1016/j.infsof.2005.07.005 fatcat:rvycgjhwrvfhdfvpvjrwysbbti

Reducing VSM data sparseness by generalizing contexts: application to health text mining

Amandine Périnet, Thierry Hamon
2014 Proceedings of the 5th International Workshop on Health Text Mining and Information Analysis (Louhi)  
Vector Space Models are limited with low frequency words due to few available contexts and data sparseness.  ...  To tackle this problem, we generalize contexts by integrating semantic relations acquired with linguistic approaches. We use three methods that acquire hypernymy relations on a EHR corpus.  ...  We discuss here the results we obtain for terms, for the two thresholds on the similarity score: a low and a higher thresholds, with relations with a similarity above 0.0005 and above 0.001.  ... 
doi:10.3115/v1/w14-1114 dblp:conf/acl-louhi/PerinetH14 fatcat:cuo752xxdvcx3immw43xfkzoqq

Efficient implementation of associative classifiers for document classification

Yongwook Yoon, Gary Geunbae Lee
2007 Information Processing & Management  
We propose a feature selection based on the mutual information between the word and class variables to reduce the space dimension of the associative classifiers.  ...  In addition, the training process of the associative classifier produces a huge amount of classification rules, which makes the prediction with a new document ineffective.  ...  The procedure of acquiring matching rules is very similar to the rule pruning procedure.  ... 
doi:10.1016/j.ipm.2006.07.012 fatcat:qmrreskyabe2nfzwjfkwyd5pw4

Mining association language patterns using a distributional semantic model for negative life event classification

Liang-Chih Yu, Chien-Lung Chan, Chao-Cheng Lin, I-Chun Lin
2011 Journal of Biomedical Informatics  
The data mining algorithm, called association rule mining, was used to generate a set of seed patterns by incrementally associating frequently co-occurring words from a small corpus of sentences labeled  ...  This study describes the use of association language patterns, i.e., meaningful combinations of words (e.g., ), as features to classify sentences with negative life events into predefined categories (e.g  ...  Thus, the task of association rule mining is to mine the language patterns of frequently associated words from the training sentences.  ... 
doi:10.1016/j.jbi.2011.01.006 pmid:21292030 fatcat:fwsrg4yamrbc3p2zmj6vl7l7gy

Intelligent Filling Method of Power Grid Working Ticket Based on Historical Ticket Knowledge Base

Zhiguo An, Mancheng Yi, Jing Liu, Ying Li, Zheng Peng, Sifan Yu, Jianxin Liu, Weirong Huang, Chunhua Fang
2021 Frontiers in Energy Research  
Firstly, the historical ticket data are preprocessed, then the historical ticket information is mined by the association rule algorithm, and the method of establishing the historical ticket knowledge base  ...  The method enables the identification and extraction of similar and associated work tickets, improves the efficiency of filling work tickets for power grids, and promotes the intelligence of the safety  ...  The similarity of the first two texts under the traditional model is higher.  ... 
doi:10.3389/fenrg.2021.813855 fatcat:nc3xpfsmc5e6phzuczef6nx7jq

Incorporating terminology evolution for query translation in text retrieval with association rules

Amal C. Kaluarachchi, Aparna S. Varde, Srikanta Bedathur, Gerhard Weikum, Jing Peng, Anna Feldman
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
In order to discover SITACs, we propose an approach based on a novel framework constituting an integration of natural language processing, association rule mining and contextual similarity as a learning  ...  The proposed approach has been experimented with real data and has been found to yield good results with respect to efficiency and accuracy.  ...  This is justified by the fact that such rule mining is in line with the logic of humans associating concepts.  ... 
doi:10.1145/1871437.1871730 dblp:conf/cikm/KaluarachchiVBWPF10 fatcat:zeew7ywctfcfhasutkoiiov5je

Learning to Classify Biomedical Terms Through Literature Mining and Genetic Algorithms [chapter]

Irena Spasić, Goran Nenadić, Sophia Ananiadou
2004 Lecture Notes in Computer Science  
First, each term is associated with the most frequently co-occurring CP. Classes attached to such CP are initially suggested as the term's potential classes.  ...  Then, the term is finally mapped to the most similar suggested class.  ...  Based on the training set, CPs were associated with the CSs, e.g. the pattern V:activate PREP:by TERM was associated with the following CS: {immunologic factor, receptor, enzyme, hormone, pharmacologic  ... 
doi:10.1007/978-3-540-28651-6_51 fatcat:dw6cp6ifczardap5xkaymyarzm

Web Translation Mining Based on Suffix Arrays

Gaolin Fang, Hao Yu
2007 International Journal of Asian Language Processing  
In this paper, after reviewing and analyzing all possible methods of acquiring translations, a statistics method based on suffix arrays is proposed to mine term translations from the Web.  ...  methods are respectively proposed to deal with subset redundancy information and affix redundancy information formed in the process of estimation.  ...  However, the method is related with the language, and is difficult to be extended to similar languages. 4) Acquiring translation from non-parallel corpora Acquiring translation from non-parallel corpora  ... 
dblp:journals/jclc/FangY07 fatcat:mf5ejw55ubcn3klyett766z4uq

Grade Prediction via Prior Grades and Text Mining on Course Descriptions: Course Outlines and Intended Learning Outcomes

Jiawei Li, S. Supraja, Wei Qiu, Andy W. H. Khong, Antonija Mitrovic, Nigel Bosch
2022 Zenodo  
In addition, we classify intended learning outcomes according to their higher- or lower-order thinking skills.  ...  Past academic achievements are then fused with the above features for grade prediction.  ...  being associated with the highest-order thinking skill [20] .  ... 
doi:10.5281/zenodo.6853171 fatcat:findvcrb45bynk6unipdf5tjgu

Wavelet-based higher-order neural networks for mine detection in thermal IR imagery

Brian A. Baertlein, Wen-Jiao Liao, Abinash C. Dubey, James F. Harvey, J. Thomas Broach, Regina E. Dugan
2000 Detection and Remediation Technologies for Mines and Minelike Targets V  
The well-known memory limitations that arise with higher-order neural networks are addressed by (1) the data compression capabilities of wavelet packets, (2) projections of the image data into a space  ...  of similar triangles, and (3) quantization of that "triangle space."  ...  Use of the wavelet transform and a subsequent projection into "triangle space" greatly reduces the well-known memory problems associated with higher-order neural networks.  ... 
doi:10.1117/12.396244 fatcat:3sn7uflhtrberl52aohq6moxyq

Knowledge Acquisition and Corpus for Argumentation-Based Chatbots

Lisa Andreevna Chalaguine, Anthony Hunter
2019 International Conference of the Italian Association for Artificial Intelligence  
In order to succeed, the chatbot also needs to be aware of various arguments and the interplay between them.  ...  In this paper, we propose a method to acquire a large number of arguments in a graph structure using crowd sourcing.  ...  The threshold as to how often a word has to appear in order to be considered "common" also rises since the number of arguments increases with each depth.  ... 
dblp:conf/aiia/ChalaguineH19 fatcat:5fr5hh5snbcpfhpqlccjwb6xhq

Experimental study of discovering essential information from customer inquiry

Keiko Shimazu, Atsuhito Momma, Koichi Furukawa
2003 Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '03  
It has been claimed that association rule mining is not suited for text mining.  ...  The association rules were induced regarding each pair of words as an item.  ...  The three rule mining algorithms, (1) typical association rule mining algorithm [1] , (2) association rule mining with a novel rule selection threshold, the difference between prior and posterior confidence  ... 
doi:10.1145/956750.956850 dblp:conf/kdd/ShimazuMF03 fatcat:ulqqzlixa5gsncei4uuhyyyxmu

Experimental study of discovering essential information from customer inquiry

Keiko Shimazu, Atsuhito Momma, Koichi Furukawa
2003 Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '03  
It has been claimed that association rule mining is not suited for text mining.  ...  The association rules were induced regarding each pair of words as an item.  ...  The three rule mining algorithms, (1) typical association rule mining algorithm [1] , (2) association rule mining with a novel rule selection threshold, the difference between prior and posterior confidence  ... 
doi:10.1145/956841.956850 fatcat:7m7musl7hfealngaicf2clb66a

Event Relation Acquisition Using Dependency Patterns and Confidence-Weighted Co-occurrence Statistics

Shohei Higashiyama, Kunihiko Sadamasa, Takashi Onishi, Yotaro Watanabe
2017 Proceedings of the 2017 Federated Conference on Computer Science and Information Systems  
Experimental results show that the proposed method can acquire a larger amount of positive relation instances while keeping higher precision compared with the existing method and the proposed method also  ...  However, in the case of domain-specific knowledge acquisition, such a method can not acquire much knowledge due to the limited amount of available knowledge sources.  ...  Association rule mining methods extract subsets of items with strong association from given sets of items as association rules.  ... 
doi:10.15439/2017f419 dblp:conf/fedcsis/HigashiyamaSOW17 fatcat:i3fuomt4rjambgz5kwpdhdkqi4
« Previous Showing results 1 — 15 out of 115,491 results