[go: up one dir, main page]

TW200602898A - A method for adaptive hierarchical news story clustering based on semantic understanding - Google Patents

A method for adaptive hierarchical news story clustering based on semantic understanding

Info

Publication number
TW200602898A
TW200602898A TW093120433A TW93120433A TW200602898A TW 200602898 A TW200602898 A TW 200602898A TW 093120433 A TW093120433 A TW 093120433A TW 93120433 A TW93120433 A TW 93120433A TW 200602898 A TW200602898 A TW 200602898A
Authority
TW
Taiwan
Prior art keywords
news video
clustering
semantic understanding
hierarchical
stories
Prior art date
Application number
TW093120433A
Other languages
Chinese (zh)
Inventor
Jhing-Fa Wang
Jia-Ching Wang
Chen-Yu Chen
Cheng-Ping Chen
Original Assignee
Jhing-Fa Wang
Jia-Ching Wang
Chen-Yu Chen
Cheng-Ping Chen
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jhing-Fa Wang, Jia-Ching Wang, Chen-Yu Chen, Cheng-Ping Chen filed Critical Jhing-Fa Wang
Priority to TW093120433A priority Critical patent/TW200602898A/en
Publication of TW200602898A publication Critical patent/TW200602898A/en

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

This invention presents a method for news video story clustering based on unsupervised learning. In this invention, the news video stories are clustered by the semantic understanding of the captions. This invention shows that it doesn't require any pre-defined class label, because the news video stories are clustered based on their content similarities. In addition to this, this invention forms a hierarchical clustering structure. According to the above mentioned method, a hierarchical tree for news video categorization can be built. The root node represents all the news video stories. Each tree node may further be separated to several sub-nodes by clustering. To avoid over-learning, this invention presents a criterions based on entropy to prevent further separating a tree node.
TW093120433A 2004-07-07 2004-07-07 A method for adaptive hierarchical news story clustering based on semantic understanding TW200602898A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW093120433A TW200602898A (en) 2004-07-07 2004-07-07 A method for adaptive hierarchical news story clustering based on semantic understanding

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW093120433A TW200602898A (en) 2004-07-07 2004-07-07 A method for adaptive hierarchical news story clustering based on semantic understanding

Publications (1)

Publication Number Publication Date
TW200602898A true TW200602898A (en) 2006-01-16

Family

ID=57807028

Family Applications (1)

Application Number Title Priority Date Filing Date
TW093120433A TW200602898A (en) 2004-07-07 2004-07-07 A method for adaptive hierarchical news story clustering based on semantic understanding

Country Status (1)

Country Link
TW (1) TW200602898A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI700925B (en) * 2018-01-04 2020-08-01 良知股份有限公司 Digital news film screening and notification methods

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI700925B (en) * 2018-01-04 2020-08-01 良知股份有限公司 Digital news film screening and notification methods

Similar Documents

Publication Publication Date Title
Schuller et al. Speaker independent emotion recognition by early fusion of acoustic and linguistic features within ensembles
Reiter An architecture for data-to-text systems
WO2005009205A3 (en) System and method for self management of health using natural language interface
EP1197950A3 (en) Hierarchized dictionaries for speech recognition
Grósz et al. Wav2vec2-based paralinguistic systems to recognise vocalised emotions and stuttering
Cornips et al. External and internal factors in bilingual and bidialectal language development: Grammatical gender of the Dutch definite determiner
CA2461777A1 (en) Linguistically informed statistical models of constituent structure for ordering in sentence realization for a natural language generation system
EP1801714A3 (en) Generation of descriptions for classes and clusters of documents
WO2003096350A3 (en) Scalable video summarization
WO2016199160A3 (en) Language processing and knowledge building system
WO2012057559A3 (en) Intelligent emotion-inferring apparatus, and inferring method therefor
EP4113325A3 (en) System and method of saving digital content classified by person-based clustering
WO2012057560A3 (en) Intelligent emotional word expanding apparatus and expanding method therefor
EP0817169A3 (en) Method and system for encoding pronunciation prefix trees
US12333252B2 (en) Automated system and method to prioritize language model and ontology expansion and pruning
WO2004090797A3 (en) Decision tree analysis
ÖZçALIŞKAN Learning to talk about spatial motion in language-specific ways
TW200602898A (en) A method for adaptive hierarchical news story clustering based on semantic understanding
Oh et al. Jujeop: Korean puns for k-pop stars on social media
Luján Spanish in the Americas
Hyman Vowel harmony in Gunu
Niketić Conceptual blending in English and Serbian question-and-answer jokes
Woodbury The loss of a phoneme
Kavari et al. Multiple noun class prefixes in Otjiherero
Dingwall Ravenous wolves and cuddly bears: Predators in everyday