Concordance

Query P05-1056 20 >
Random sample 20 (640.3 per million)

tech,0-1-P05-1056,ak	Evaluation on the <term> ACE corpus </term> shows that effective incorporation of diverse <term> features </term> enables our system outperform previously best-reported systems on the 24 <term> ACE relation subtypes </term> and significantly outperforms <term> tree kernel-based systems </term> by over 20 in <term> F-measure </term> on the 5 <term> ACE relation types </term> . <term> Sentence boundary detection </term> in <term> speech </term> is important for enriching <term> speech recognition output </term> , making it easier for humans to read and downstream modules to process .	#9422 Evaluation on the ACE corpus shows that effective incorporation of diverse features enables our system outperform previously best-reported systems on the 24 ACE relation subtypes and significantly outperforms tree kernel-based systems by over 20 in F-measure on the 5 ACE relation types.Sentence boundary detection in speech is important for enriching speech recognition output, making it easier for humans to read and downstream modules to process.
other,4-1-P05-1056,ak	<term> Sentence boundary detection </term> in <term> speech </term> is important for enriching <term> speech recognition output </term> , making it easier for humans to read and downstream modules to process .	#9426 Sentence boundary detection inspeech is important for enriching speech recognition output, making it easier for humans to read and downstream modules to process.
other,9-1-P05-1056,ak	<term> Sentence boundary detection </term> in <term> speech </term> is important for enriching <term> speech recognition output </term> , making it easier for humans to read and downstream modules to process .	#9431 Sentence boundary detection in speech is important for enrichingspeech recognition output, making it easier for humans to read and downstream modules to process.
tech,7-2-P05-1056,ak	In previous work , we have developed <term> hidden Markov model ( HMM ) and maximum entropy ( Maxent ) classifiers </term> that integrate <term> textual and prosodic knowledge sources </term> for detecting <term> sentence boundaries </term> .	#9455 In previous work, we have developedhidden Markov model ( HMM ) and maximum entropy ( Maxent ) classifiers that integrate textual and prosodic knowledge sources for detecting sentence boundaries.
other,22-2-P05-1056,ak	In previous work , we have developed <term> hidden Markov model ( HMM ) and maximum entropy ( Maxent ) classifiers </term> that integrate <term> textual and prosodic knowledge sources </term> for detecting <term> sentence boundaries </term> .	#9470 In previous work, we have developed hidden Markov model (HMM) and maximum entropy (Maxent) classifiers that integratetextual and prosodic knowledge sources for detecting sentence boundaries.
other,29-2-P05-1056,ak	In previous work , we have developed <term> hidden Markov model ( HMM ) and maximum entropy ( Maxent ) classifiers </term> that integrate <term> textual and prosodic knowledge sources </term> for detecting <term> sentence boundaries </term> .	#9477 In previous work, we have developed hidden Markov model (HMM) and maximum entropy (Maxent) classifiers that integrate textual and prosodic knowledge sources for detectingsentence boundaries.
tech,10-3-P05-1056,ak	In this paper , we evaluate the use of a <term> conditional random field ( CRF ) </term> for this task and relate results with this <term> model </term> to our prior work .	#9490 In this paper, we evaluate the use of aconditional random field ( CRF ) for this task and relate results with this model to our prior work.
tech,24-3-P05-1056,ak	In this paper , we evaluate the use of a <term> conditional random field ( CRF ) </term> for this task and relate results with this <term> model </term> to our prior work .	#9504 In this paper, we evaluate the use of a conditional random field (CRF) for this task and relate results with thismodel to our prior work.
lr,4-4-P05-1056,ak	We evaluate across two <term> corpora </term> ( conversational telephone speech and broadcast news speech ) on both <term> human transcriptions </term> and <term> speech recognition output </term> .	#9514 We evaluate across twocorpora (conversational telephone speech and broadcast news speech) on both human transcriptions and speech recognition output.
other,16-4-P05-1056,ak	We evaluate across two <term> corpora </term> ( conversational telephone speech and broadcast news speech ) on both <term> human transcriptions </term> and <term> speech recognition output </term> .	#9526 We evaluate across two corpora (conversational telephone speech and broadcast news speech) on bothhuman transcriptions and speech recognition output.
other,19-4-P05-1056,ak	We evaluate across two <term> corpora </term> ( conversational telephone speech and broadcast news speech ) on both <term> human transcriptions </term> and <term> speech recognition output </term> .	#9529 We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions andspeech recognition output.
model,4-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9537 In general, ourCRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
measure(ment),9-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9542 In general, our CRF model yields a lowererror rate than the HMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
model,13-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9546 In general, our CRF model yields a lower error rate than theHMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
other,19-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9552 In general, our CRF model yields a lower error rate than the HMM and Maxent models on theNIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
other,25-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9558 In general, our CRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task inspeech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
tech,40-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9573 In general, our CRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved bythree-way voting among the classifiers.
tech,44-5-P05-1056,ak	In general , our <term> CRF model </term> yields a lower <term> error rate </term> than the <term> HMM and Maxent models </term> on the <term> NIST sentence boundary detection task </term> in <term> speech </term> , although it is interesting to note that the best results are achieved by <term> three-way voting </term> among the <term> classifiers </term> .	#9577 In general, our CRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task in speech, although it is interesting to note that the best results are achieved by three-way voting among theclassifiers.
model,5-6-P05-1056,ak	This probably occurs because each <term> model </term> has different strengths and weaknesses for modeling the <term> knowledge sources </term> .	#9584 This probably occurs because eachmodel has different strengths and weaknesses for modeling the knowledge sources.
other,14-6-P05-1056,ak	This probably occurs because each <term> model </term> has different strengths and weaknesses for modeling the <term> knowledge sources </term> .	#9593 This probably occurs because each model has different strengths and weaknesses for modeling theknowledge sources.


	in Help