A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Word sense disambiguation with pattern learning and automatic feature selection
2002
Natural Language Engineering
Resolving Sense Ambiguity of Korean Nouns Based on Concept Co-occurrence Information
2003
Australasian Language Technology Association Workshop
The sense-tagged corpus may serve as a knowledge source to extract useful clues for word sense disambiguation (WSD). ...
Also, we show that the performance of word sense disambiguation can be improved by combining several base classifiers. ...
Acknowledgements This work was supported by the Korea Science and Engineering Foundation (KOSEF) through the Advanced Information Technology Research Center(AITrc). ...
dblp:conf/acl-alta/ChungL03
fatcat:lcglq4nkmbgu3d6rmfy6ltucuq
Pattern Learning and Active Feature Selection for Word Sense Disambiguation
2001
International Workshop on Semantic Evaluation
The algorithm has two main components (1) pattern learning from available sense tagged corpora (SemCor) and dictionary definitions (WordNet), and (2) instance based learning with active feature selection ...
These systems have participated in the SENSEVAL-2 competition attaining the best performance for both English all words and English lexical sample tasks 1 . ...
It illustrates the two main components, namely pattern learning from available sense tagged corpora and dictionary definitions and instance based learning with active feature selection. ...
dblp:conf/semeval/MihalceaM01
fatcat:hdmi7c4xxjcoth5hi5szr4m6jq
A Decision Tree Based Word Sense Disambiguation System in Manipuri Language
2014
Advanced Computing An International Journal
Conventional positional and context based features are suggested to capture the sense of the words, which have ambiguous and multiple senses. ...
KEYWORDS Word sense disambiguation(WSD); Classification and regression tree (CART); polysemous word; Manipuri. ...
Being trained on 1,600 words and tested on 400 words using 7 features, the word sense disambiguation system predicts the senses with 71.75% accuracy. ...
doi:10.5121/acij.2014.5403
fatcat:xsrrs3svl5dqpms5he4kmspuiq
Word Sense Discrimination
[chapter]
2017
Encyclopedia of Machine Learning and Data Mining
The correct sense of an ambiguous word can be selected based on the context where it occurs, and correspondingly the problem of word sense disambiguation is defined as the task of automatically assigning ...
Given a target word and a set of examples where this word occurs, each occurrence being annotated with the correct sense, a supervised system will attempt to learn how to automatically annotate occurrences ...
doi:10.1007/978-1-4899-7687-1_883
fatcat:kruczwhjlndyjl3zesk2qqxmoi
Sense information for disambiguation
2002
Proceedings of the ACL-02 workshop on Word sense disambiguation recent successes and future directions -
We report here the contribution of default sense selection, idiomatic usage, syntactic and semantic clues, subcategorization patterns, word forms, syntactic usage, context, selectional preferences, and ...
Finally, we compare these features to those identified as significant in supervised learning approaches. 1 We have not yet determined how decisive these features are in making correct sense selections. ...
, Adam Kilgarriff, and James McCracken for their invaluable discussions, to Rada Mihalcea, Ted Pedersen, and David Tugwell for making their data available, and to the anonymous reviewers. ...
doi:10.3115/1118675.1118682
dblp:conf/semeval/Litkowski02a
fatcat:urnklvk5ufbglnmztt72ibyixu
Page 159 of Computational Linguistics Vol. 30, Issue 2
[page]
2004
Computational Linguistics
We use a context-free grammar to specify the type of patterns that are the best indicators of a semantic interrelationship and to select the appropriate sense configurations accordingly. ...
Creating a graph representation for word senses. A graph representation of word senses is automatically built using a variety of knowledge source:
WordNet. ...
Learning to Link Grammar and Encyclopedic Information of Assist ESL Learners
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
The method involves word sense disambiguation on target words, automatically parsing the sentences in a large-scale corpus, automatically generating grammar patterns, collocations, examples, and quizzes ...
for every target word, and automatically linking named entities to corresponding Wikipedia information. ...
To form questions, we select representative examples containing the target word with the word sense in the user-submitted content from CAM. ...
doi:10.18653/v1/p19-3034
dblp:conf/acl/ChenYHTHTTHC19
fatcat:a3hckkadjnbtto56gc2qkzhuya
Automatic sense disambiguation for acronyms
2004
Proceedings of the 27th annual international conference on Research and development in information retrieval - SIGIR '04
A machine learning methodology for the disambiguation of acronym senses is presented, which starts from an acronym sense dictionary. ...
Leaveone-out cross-validation on 9,963 documents with 47 acronym forms achieves accuracy 92.58% and ¬ ½ =91.52%. ...
The decision task is based on the result of "pattern recognition" using the learned classification model for the acronym sense, applied to the target document's feature vector. ...
doi:10.1145/1008992.1009133
dblp:conf/sigir/Zahariev04
fatcat:isvezpps6jb5rds636zlap2zti
Structural semantic interconnections: a knowledge-based approach to word sense disambiguation
2005
IEEE Transactions on Pattern Analysis and Machine Intelligence
Index Terms-Natural language processing, ontology learning, structural pattern matching, word sense disambiguation. ae IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 7, JULY ...
Word Sense Disambiguation (WSD) is traditionally considered an AI-hard problem. ...
The authors warmly thank Francesco Sclano who helped them with their heavy experiments. ...
doi:10.1109/tpami.2005.149
pmid:16013755
fatcat:3za2wf7itvc37jpaxc7gwdneom
Homograph Disambiguation through Selective Diacritic Restoration
2019
Proceedings of the Fourth Arabic Natural Language Processing Workshop
In this paper, we propose approaches for automatically marking a subset of words for diacritic restoration, which leads to selective homograph disambiguation. ...
Compared to full or no diacritic restoration, these approaches yield selectively-diacritized datasets that balance sparsity and lexical disambiguation. ...
Sense Induction Based Approach (SENSE): Selective diacritization is related to word sense disambiguation, however we only target disambiguation through diacritic restoration. ...
doi:10.18653/v1/w19-4606
dblp:conf/wanlp/AlqahtaniAD19
fatcat:jhquykoxvncpvicmnkqqhgs26a
Text Document Classification by using WordNet Ontology and Neural Network
2018
International Journal of Computer Applications
The closest ancestors of the senses of all the words in a given document are selected as folders for the specified document. ...
We propose a method of automatic text classification using Convolutional Neural Network based on the disambiguation of the meaning of the word we use the WordNet ontology and word embedding algorithm to ...
Step 5: Create one pattern vector for each document with the features (i.e. words) selected in step 3. ...
doi:10.5120/ijca2018918229
fatcat:kjf7cugzwjhrnn7fiw7dhaswva
A Survey of Word-sense Disambiguation Effective Techniques and Methods for Indian Languages
2013
Journal of Emerging Technologies in Web Intelligence
Word Sense Disambiguation is a challenging technique in Natural Language Processing. ...
There are some words in the natural languages which can cause ambiguity about the sense of the word.WSD identifies the correct sense of the word in a sentence or a document. ...
Word Sense Disambiguation [1] is a task of automatically assigning a correct sense to the words which are polysemous in a particular context. ...
doi:10.4304/jetwi.5.4.354-360
fatcat:exrjgd3al5as7acxwcnuoomggy
Word Sense Disambiguation Using Neural Networks with Concept Co-occurrence Information
2001
Natural Language Processing Pacific Rim Symposium
Most previous word sense disambiguation approaches based on neural networks were impractical due to their huge feature set size. ...
We propose a method for resolving word sense ambiguity using neural networks with refined concept co-occurrence information (CCI) as features. ...
Acknowledgements The authors would like to thank the Ministry of Education of Korea for its financial support toward the Electrical and Computer Engineering ...
dblp:conf/nlprs/ChungKML01
fatcat:bgrilnrn6zbqbkmbkb5pmryqem
Learning Rules for Large-Vocabulary Word Sense Disambiguation: A Comparison of Various Classifiers
[chapter]
2000
Lecture Notes in Computer Science
This study compares decision tree induction with other popular learning methods and discusses their advantages and disadvantages. ...
In this article we compare the performance of various machine learning algorithms on the task of constructing word-sense disambiguation rules from data. ...
Concluding Remarks and Further Work Machine learning algorithms are a promising approach to the automatic construction of word sense disambiguators. ...
doi:10.1007/3-540-45154-4_35
fatcat:hzo5eor2gjeyrpreuusvtqd7ji
« Previous
Showing results 1 — 15 out of 12,531 results