Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022937510> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3022937510 endingPage "604" @default.
- W3022937510 startingPage "589" @default.
- W3022937510 abstract "Named Entity Recognition (NER) aims to classify each word of a document into predefined target named entity classes and is now-a-days considered to be fundamental for many Natural Language Processing (NLP) tasks such as information retrieval, machine translation, information extraction, question answering systems and others. This paper reports about the development of a NER system for Bengali and Hindi using Support Vector Machine (SVM). Though this state of the art machine learning technique has been widely applied to NER in several well-studied languages, the use of this technique to Indian languages (ILs) is very new. The system makes use of the different contextual information of the words along with the variety of features that are helpful in predicting the four different named (NE) classes, such as Person name, Location name, Organization name and Miscellaneous name. We have used the annotated corpora of 122,467 tokens of Bengali and 502,974 tokens of Hindi tagged with the twelve different NE classes , defined as part of the IJCNLP-08 NER Shared Task for South and South East Asian Languages (SSEAL) . In addition, we have manually annotated 150K wordforms of the Bengali news corpus, developed from the web-archive of a leading Bengali newspaper. We have also developed an unsupervised algorithm in order to generate the lexical context patterns from a part of the unlabeled Bengali news corpus. Lexical patterns have been used as the features of SVM in order to improve the system performance. The NER system has been tested with the gold standard test sets of 35K, and 60K tokens for Bengali, and Hindi, respectively. Evaluation results have demonstrated the recall, precision, and f-score values of 88.61%, 80.12%, and 84.15%, respectively, for Bengali and 80.23%, 74.34%, and 77.17%, respectively, for Hindi. Results show the improvement in the f-score by 5.13% with the use of context patterns. Statistical analysis, ANOVA is also performed to compare the performance of the proposed NER system with that of the existing HMM based system for both the languages. Keywords—Named Entity (NE); Named Entity Recognition (NER); Support Vector Machine (SVM); Bengali; Hindi." @default.
- W3022937510 created "2020-05-13" @default.
- W3022937510 creator A5006218020 @default.
- W3022937510 creator A5085370631 @default.
- W3022937510 date "2010-03-23" @default.
- W3022937510 modified "2023-09-23" @default.
- W3022937510 title "Named Entity Recognition using Support Vector Machine: A Language Independent Approach" @default.
- W3022937510 hasPublicationYear "2010" @default.
- W3022937510 type Work @default.
- W3022937510 sameAs 3022937510 @default.
- W3022937510 citedByCount "5" @default.
- W3022937510 countsByYear W30229375102014 @default.
- W3022937510 countsByYear W30229375102015 @default.
- W3022937510 crossrefType "journal-article" @default.
- W3022937510 hasAuthorship W3022937510A5006218020 @default.
- W3022937510 hasAuthorship W3022937510A5085370631 @default.
- W3022937510 hasConcept C12267149 @default.
- W3022937510 hasConcept C151730666 @default.
- W3022937510 hasConcept C154945302 @default.
- W3022937510 hasConcept C162324750 @default.
- W3022937510 hasConcept C187736073 @default.
- W3022937510 hasConcept C19235068 @default.
- W3022937510 hasConcept C203005215 @default.
- W3022937510 hasConcept C204321447 @default.
- W3022937510 hasConcept C2779135771 @default.
- W3022937510 hasConcept C2779343474 @default.
- W3022937510 hasConcept C2780451532 @default.
- W3022937510 hasConcept C41008148 @default.
- W3022937510 hasConcept C44291984 @default.
- W3022937510 hasConcept C519982507 @default.
- W3022937510 hasConcept C86803240 @default.
- W3022937510 hasConceptScore W3022937510C12267149 @default.
- W3022937510 hasConceptScore W3022937510C151730666 @default.
- W3022937510 hasConceptScore W3022937510C154945302 @default.
- W3022937510 hasConceptScore W3022937510C162324750 @default.
- W3022937510 hasConceptScore W3022937510C187736073 @default.
- W3022937510 hasConceptScore W3022937510C19235068 @default.
- W3022937510 hasConceptScore W3022937510C203005215 @default.
- W3022937510 hasConceptScore W3022937510C204321447 @default.
- W3022937510 hasConceptScore W3022937510C2779135771 @default.
- W3022937510 hasConceptScore W3022937510C2779343474 @default.
- W3022937510 hasConceptScore W3022937510C2780451532 @default.
- W3022937510 hasConceptScore W3022937510C41008148 @default.
- W3022937510 hasConceptScore W3022937510C44291984 @default.
- W3022937510 hasConceptScore W3022937510C519982507 @default.
- W3022937510 hasConceptScore W3022937510C86803240 @default.
- W3022937510 hasIssue "3" @default.
- W3022937510 hasLocation W30229375101 @default.
- W3022937510 hasOpenAccess W3022937510 @default.
- W3022937510 hasPrimaryLocation W30229375101 @default.
- W3022937510 hasRelatedWork W1506869973 @default.
- W3022937510 hasRelatedWork W1835859732 @default.
- W3022937510 hasRelatedWork W1839756413 @default.
- W3022937510 hasRelatedWork W2005046969 @default.
- W3022937510 hasRelatedWork W2029503862 @default.
- W3022937510 hasRelatedWork W2046620867 @default.
- W3022937510 hasRelatedWork W2056515769 @default.
- W3022937510 hasRelatedWork W2095452022 @default.
- W3022937510 hasRelatedWork W2107524433 @default.
- W3022937510 hasRelatedWork W2188642484 @default.
- W3022937510 hasRelatedWork W2250597603 @default.
- W3022937510 hasRelatedWork W2403176590 @default.
- W3022937510 hasRelatedWork W2600299847 @default.
- W3022937510 hasRelatedWork W2756253150 @default.
- W3022937510 hasRelatedWork W2769530083 @default.
- W3022937510 hasRelatedWork W2987972909 @default.
- W3022937510 hasRelatedWork W3206914982 @default.
- W3022937510 hasRelatedWork W3208185100 @default.
- W3022937510 hasRelatedWork W2101230831 @default.
- W3022937510 hasRelatedWork W2511874079 @default.
- W3022937510 hasVolume "4" @default.
- W3022937510 isParatext "false" @default.
- W3022937510 isRetracted "false" @default.
- W3022937510 magId "3022937510" @default.
- W3022937510 workType "article" @default.