Extraction and comparison of various prosodic feature sets on sentence segmentation task for Turkish Broadcast News data

2014 ◽  
Author(s):  
Dogan Dalva ◽  
Izel D. Revidi ◽  
Umit Guz ◽  
Hakan Gurkan
Keyword(s):  
Broadcast News ◽  
Feature Sets ◽  
Prosodic Feature ◽  
Sentence Segmentation ◽  
Segmentation Task

scholarly journals CROSS-GENRE FEATURE COMPARISONS FOR SPOKEN SENTENCE SEGMENTATION

2007 ◽  
Vol 01 (03) ◽  
pp. 335-346
Author(s):  
SEBASTIEN CUENDET ◽  
DILEK HAKKANI-TUR ◽  
ELIZABETH SHRIBERG ◽  
JAMES FUNG ◽  
BENOIT FAVRE
Keyword(s):  
Natural Language Processing ◽  
Language Processing ◽  
Spoken Language ◽  
Prosodic Features ◽  
Forward Selection ◽  
Feature Sets ◽  
Large Size ◽  
Sentence Segmentation ◽  
Speech Data ◽  
Selection For

Automatic sentence segmentation of spoken language is an important precursor to downstream natural language processing. Previous studies combine lexical and prosodic features, but can impose significant computational challenges because of the large size of feature sets. Little is understood about which features most benefit performance, particularly for speech data from different speaking styles. We compare sentence segmentation for speech from broadcast news versus natural multi-party meetings, using identical lexical and prosodic feature sets across genres. Results based on boosting and forward selection for this task show that (1) features sets can be reduced with little or no loss in performance, and (2) the contribution of different feature types differs significantly by genre. We conclude that more efficient approaches to sentence segmentation and similar tasks can be achieved, especially if genre differences are taken into account.

A Psychological View of Broadcast News

1989 ◽  
Vol 34 (6) ◽  
pp. 595-595
Author(s):  
Roger Jon Desmond
Keyword(s):  
Broadcast News ◽  
Psychological View

Arabic named entity recognition using optimized feature sets

2008 ◽  
Author(s):  
Yassine Benajiba ◽  
Mona Diab ◽  
Paolo Rosso
Keyword(s):  
Named Entity Recognition ◽  
Entity Recognition ◽  
Feature Sets ◽  
Named Entity

Headline Generation for Written and Broadcast News

2005 ◽  
Author(s):  
David Zajic ◽  
Bonnie Dorr ◽  
Richard Schwartz
Keyword(s):  
Broadcast News

Detection and Recovery of OOVs for Improved English Broadcast News Captioning

2019 ◽  
Author(s):  
Samuel Thomas ◽  
Kartik Audhkhasi ◽  
Zoltán Tüske ◽  
Yinghui Huang ◽  
Michael Picheny
Keyword(s):  
Broadcast News

Hybrid Model using Firefly and BBO for Feature Selection in Software Product Line

2020 ◽  
Vol 13 ◽  
Author(s):  
Hitesh Yadav ◽  
Rita Chhikara ◽  
Charan Kumari
Keyword(s):  
Hybrid Model ◽  
High Performance ◽  
Software Product Line ◽  
Product Line ◽  
Feature Model ◽  
Software Systems ◽  
Feature Sets ◽  
Research Article ◽  
Software Product ◽  
Multiple Variants

Background: Software Product Line is the group of multiple software systems which share the similar set of features with multiple variants. Feature model is used to capture and organize features used in different multiple organization. Objective: The objective of this research article is to obtain an optimized subset of features which are capable of providing high performance. Methods: In order to achieve the desired objective, two methods have been proposed. a) An improved objective function which is used to compute the contribution of each feature with weight based methodology. b) A hybrid model is employed to optimize the Software Product Line problem. Results: Feature sets varying in size from 100 to 1000 have been used to compute the performance of the Software Product Line. Conclusion: The results shows that proposed hybrid model outperforms the state of art metaheuristic algorithms.

Sign in / Sign up

Export Citation Format

Share Document