1,392 Hits in 8.8 sec

Word sense disambiguation by learning from unlabeled data

Seong-Bae Park, Byoung-Tak Zhang, Yung Taek Kim
2000 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics - ACL '00  
In this paper we describe a machine learning approach to word sense disambiguation that uses unlabeled data. Our method is based on selective sampling with committees of decision trees.  ...  Using additional unlabeled examples, therefore, improves the performance of word sense disambiguation and minimizes the cost of manual labeling.  ...  These 11 grammatical functions are from the parser, KEMTS (Korean-to-English Machine Translation System) developed in Seoul National University, Korea.  ... 
doi:10.3115/1075218.1075287 dblp:conf/acl/ParkZK00 fatcat:h43frgnqejd5voifdsodgnukma

An Insight into Word Sense Disambiguation Techniques

Harsimran Singh, Vishal Gupta
2015 International Journal of Computer Applications  
This paper presents various techniques used in the area of Word Sense Disambiguation (WSD).  ...  Then there are also semi supervised approaches which use semi annotated corpus as reference data along with unlabeled data.  ...  But in unsupervised learning, dataset have is no label. Given this unlabeled data, the unsupervised learning algorithm finds the structure in the data.  ... 
doi:10.5120/20888-3666 fatcat:igoikbgvavfetfptwinwbz5z7y

Word Sense Disambiguation : Methods and Algorithms

2020 International Journal of Engineering and Advanced Technology  
This paper discuss various technique of word sense disambiguation. In WSD we disambiguate the correct sense of target word present in the text.  ...  In Knowledge based approach a external resource is used to help in disambiguation process, but in Machine learning approach a corpus is used whether it is annotated, un-annotated or both  ...  Supervised Word Sense Disambiguation The supervised approach applied to WSD system use machine learning technique from manually created sense annotated data.  ... 
doi:10.35940/ijeat.d6696.049420 fatcat:m6xwxzd55fe2zkdzxtywqt77nu

A Word Sense Disambiguation Model for Amharic Words using Semi-Supervised Learning Paradigm

G Wassie, BP Ramesh, S Teferra, M Meshesha
2014 Science Technology and Arts Research Journal  
Article Information The main objective of this research was to design a WSD (word sense disambiguation) prototype model for Amharic words using semi-supervised learning method to extract training sets  ...  A separate data sets using five ambiguous words were prepared for the development of this Amharic WSD prototype.  ...  Adaboost yields better efficiency and tree provides good visualization of algorithms and tree structure. These good properties of Adaboost and decision tree are preserved in ADtree.  ... 
doi:10.4314/star.v3i3.25 fatcat:ecwq3pgozbfejn2wh7ebnfpiaq

A Semi-Supervised method for Persian homograph Disambiguation

Noushin Riahi, Fatemeh Sedghi
2012 20th Iranian Conference on Electrical Engineering (ICEE2012)  
One of the major challenges in the most natural languages processing (NLP) tasks such as machine translation, text to speech and text mining is Word Sense Disambiguation (WSD).  ...  The Semi-Supervised methods can solve this problem by using small tagged corpus and large untagged corpus.  ...  It also proposed a supervised method to learn the decision trees automatically.  ... 
doi:10.1109/iraniancee.2012.6292453 fatcat:4kwwj2quy5g6pkrku3hcdujg54

Word Sense Disambiguation: Hybrid Approach with Annotation Up To Certain Level – A Review

Roshan R . Karwa, M.B Chandak
2014 International Journal of Engineering Trends and Technoloy  
Word sense disambiguation is concerned with determining correct meaning of word in a given particular context.  ...  Disambiguation of a word is required in Machine Translation for lexical choice for words that have different translations for different senses and that are potentially ambiguous within a given domain,  ...  approach, the training data is totally unlabelled and to form cluster from the corpus is quite difficult.  ... 
doi:10.14445/22315381/ijett-v18p267 fatcat:ts2eguqyi5c3hec2nkmey54itm

Biomedical Word Sense Disambiguation with Word Embeddings [chapter]

Rui Antunes, Sérgio Matos
2017 Advances in Intelligent Systems and Computing  
In this paper, we present results from machine learning and knowledge-based algorithms applied to biomedical word sense disambiguation.  ...  Word sense disambiguation is an important part of this process, being responsible for assigning the proper concept to an ambiguous term.  ...  Acknowledgments This work was supported by Portuguese National Funds through FCT -Foundation for Science and Technology, in the context of the project IF/01694/2013.  ... 
doi:10.1007/978-3-319-60816-7_33 fatcat:mqrxgek455gtjbps6gojhvg63i

Word Sense Discrimination [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
The word sense disambiguation literature describes experiments with a large number of machine learning algorithms, including decision lists (Yarowsky 2000), instance-based learning (Ng and Lee 1996), Naïve  ...  Bayes and decision trees (Pedersen 1998), support vector machines (Lee and Ng 2002), and others.  ... 
doi:10.1007/978-1-4899-7687-1_883 fatcat:kruczwhjlndyjl3zesk2qqxmoi

Enhanced Associative Classification of XML Documents Supported by Semantic Concepts

N.T. Thasleena, S.C. Varghese
2015 Procedia Computer Science  
An associative classifier is constructed by eliminating irrelevant rules from the generated association rule.  ...  The proposed methodology overcomes the drawbacks of the existing technologies by accomplishing the classification by utilizing not only the structure and content features but also context.  ...  Finally prediction is performed on unlabeled document tree based on the classifier obtained from model learning.  ... 
doi:10.1016/j.procs.2015.02.011 fatcat:oh7qondcerca3iqlawi4lswwye

Identification and Disambiguation of Cognates, False Friends, and Partial Cognates Using Machine Learning Techniques

Oana Frunza, Diana Inkpen
2010 International Journal of Linguistics  
We explore various ways of combining the features by applying several Machine Learning (ML) techniques from the Weka package (Witten & Frank, 2005) .  ...  The task of disambiguating partial cognates can be seen as a coarse grain cross-language word-sense discrimination task.  ...  We want to see if the cognate and false friend annotations are helpful and more likely if the additional information that we provide helps students in the learning process.  ... 
doi:10.5296/ijl.v1i1.309 fatcat:oast4j77qbd5vnorbzrigqbuma

Semi-supervised learning of partial cognates using bilingual bootstrapping

Oana Frunza, Diana Inkpen
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
We also show that our methods perform well when using corpora from different domains.  ...  Partial cognates are pairs of words in two languages that have the same meaning in some, but not all contexts.  ...  In our experiments we use the parallel data in a different way: we use words from parallel sentences as features for Machine Learning (ML).  ... 
doi:10.3115/1220175.1220231 dblp:conf/acl/FrunzaI06 fatcat:rypucbgryfegla253l4mk5fjj4

Word sense disambiguation using label propagation based semi-supervised learning

Zheng-Yu Niu, Dong-Hong Ji, Chew Lim Tan
2005 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05  
Shortage of manually sense-tagged data is an obstacle to supervised word sense disambiguation methods.  ...  In this paper we investigate a label propagation based semisupervised learning algorithm for WSD, which combines labeled and unlabeled data in learning process to fully realize a global consistency assumption  ...  Niu is supported by A*STAR Graduate Scholarship.  ... 
doi:10.3115/1219840.1219889 dblp:conf/acl/NiuJT05 fatcat:6jypscqnjbd3dmyknwnqb5xvvy

Co-training and Self-training for Word Sense Disambiguation

Rada Mihalcea
2004 Conference on Computational Natural Language Learning  
This paper investigates the application of cotraining and self-training to word sense disambiguation.  ...  A new method that combines cotraining with majority voting is introduced, with the effect of smoothing the bootstrapping learning curves, and improving the average performance.  ...  This work was partially supported by a National Science Foundation grant IIS-0336793.  ... 
dblp:conf/conll/Mihalcea04 fatcat:s6xsms5p3nhkhlbxgssng7oadu

Determine Word Sense Based on Semantic and Syntax Information

Zhang Chun-Xiang, Sun Lu-Rong, Gao Xue-Yao
2016 International Journal of Database Theory and Application  
Word sense disambiguation (WSD) plays an important role in natural language processing fields. Semantic category is semantic knowledge and part-of-speech is syntax knowledge.  ...  In this paper, word window is opened to get semantic category and part-ofspeech of left and right adjacent words around an ambiguous word.  ...  Acknowledgement This work is supported by China Postdoctoral Science Foundation Funded Project(2014M560249) and Natural Science Foundation of Heilongjiang Province of China(F2015041).  ... 
doi:10.14257/ijdta.2016.9.2.03 fatcat:su5oapovuzdqxjnjgfukcaed2i

Investigating Problems of Semi-supervised Learning for Word Sense Disambiguation [chapter]

Anh-Cuong Le, Akira Shimazu, Le-Minh Nguyen
2006 Lecture Notes in Computer Science  
In this paper, we will investigate the use of unlabeled data for WSD within the framework of semi supervised learning, in which the original labeled dataset is iteratively extended by exploiting unlabeled  ...  Word Sense Disambiguation (WSD) is the problem of determining the right sense of a polysemous word in a given context.  ...  Acknowledgement This research is partly conducted as a program for the "Fostering Talent in Emergent Research Fields" in Special Coordination Funds for Promoting Science and Technology by the Japanese  ... 
doi:10.1007/11940098_51 fatcat:zkdtmlz7tvcmfepfj6wwvukw3i
« Previous Showing results 1 — 15 out of 1,392 results