Matches in SemOpenAlex for { <https://semopenalex.org/work/W1577152877> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W1577152877 abstract "The problem of title generation involves finding the essence of a document and expressing it in only a few words. The results of a query to the Informedia Digital Video Library are summarized through an automatically generated title for each retrieved news story. When the document is errorful, as with speech-recognized broadcast news stories, the title creation challenge becomes even greater. We implemented a set of title word selection strategies and evaluated them on an independent test corpus of 579 broadcast news documents, comparing manual transcription results to automatically recognized speech using the CMU Sphinx speech recognition system with a 64000-word broadcast news language model. Using a training collection of 21190 transcribed broadcast news stories, we trained several systems to produce appropriate title words, i.e. Naive Bayesian approach with full vocabulary, Naive Bayesian approach with limited vocabulary, nearest neighbor approach and extractive approach. The F1 results shows that the nearest neighbor approach is a quick and easy way of generating good titles for speech recognized documents (F1 = 15.2%), while a Nave Bayesian approach with limited vocabulary also does well on our F1 measure (F1 = 21.6%), which ignores word order in the titles. Overall, the results show that title generation for speech recognized news documents is possible at a level approaching the accuracy of titles generated for perfect text transcriptions. One surprising phenomenon is that extractive approach performances slightly better for speech recognized documents than for manual transcripts." @default.
- W1577152877 created "2016-06-24" @default.
- W1577152877 creator A5062546146 @default.
- W1577152877 creator A5069394608 @default.
- W1577152877 date "2000-10-16" @default.
- W1577152877 modified "2023-10-18" @default.
- W1577152877 title "Title generation for spoken broadcast news using a training corpus" @default.
- W1577152877 cites W10460571 @default.
- W1577152877 cites W160817811 @default.
- W1577152877 cites W1986913017 @default.
- W1577152877 cites W2034771957 @default.
- W1577152877 cites W2055452728 @default.
- W1577152877 cites W2130217807 @default.
- W1577152877 cites W2155368638 @default.
- W1577152877 cites W2163537793 @default.
- W1577152877 doi "https://doi.org/10.21437/icslp.2000-360" @default.
- W1577152877 hasPublicationYear "2000" @default.
- W1577152877 type Work @default.
- W1577152877 sameAs 1577152877 @default.
- W1577152877 citedByCount "14" @default.
- W1577152877 countsByYear W15771528772016 @default.
- W1577152877 countsByYear W15771528772022 @default.
- W1577152877 crossrefType "proceedings-article" @default.
- W1577152877 hasAuthorship W1577152877A5062546146 @default.
- W1577152877 hasAuthorship W1577152877A5069394608 @default.
- W1577152877 hasBestOaLocation W15771528772 @default.
- W1577152877 hasConcept C153294291 @default.
- W1577152877 hasConcept C154945302 @default.
- W1577152877 hasConcept C204321447 @default.
- W1577152877 hasConcept C205649164 @default.
- W1577152877 hasConcept C2777211547 @default.
- W1577152877 hasConcept C28490314 @default.
- W1577152877 hasConcept C41008148 @default.
- W1577152877 hasConceptScore W1577152877C153294291 @default.
- W1577152877 hasConceptScore W1577152877C154945302 @default.
- W1577152877 hasConceptScore W1577152877C204321447 @default.
- W1577152877 hasConceptScore W1577152877C205649164 @default.
- W1577152877 hasConceptScore W1577152877C2777211547 @default.
- W1577152877 hasConceptScore W1577152877C28490314 @default.
- W1577152877 hasConceptScore W1577152877C41008148 @default.
- W1577152877 hasLocation W15771528771 @default.
- W1577152877 hasLocation W15771528772 @default.
- W1577152877 hasOpenAccess W1577152877 @default.
- W1577152877 hasPrimaryLocation W15771528771 @default.
- W1577152877 hasRelatedWork W1515542156 @default.
- W1577152877 hasRelatedWork W1552159754 @default.
- W1577152877 hasRelatedWork W2148757832 @default.
- W1577152877 hasRelatedWork W2293457016 @default.
- W1577152877 hasRelatedWork W2368651715 @default.
- W1577152877 hasRelatedWork W2611614995 @default.
- W1577152877 hasRelatedWork W2789919619 @default.
- W1577152877 hasRelatedWork W3107474891 @default.
- W1577152877 hasRelatedWork W3169305685 @default.
- W1577152877 hasRelatedWork W4321496520 @default.
- W1577152877 isParatext "false" @default.
- W1577152877 isRetracted "false" @default.
- W1577152877 magId "1577152877" @default.
- W1577152877 workType "article" @default.