Filters








3,040 Hits in 3.7 sec

Robust Question Answering for Speech Transcripts Using Minimal Syntactic Analysis [chapter]

Pere R. Comas, Jordi Turmo, Mihai Surdeanu
Lecture Notes in Computer Science  
For the processing of manual transcripts we have deployed a robust factual Question Answering that uses minimal syntactic information.  ...  This paper describes the participation of the Technical University of Catalonia in the CLEF 2007 Question Answering on Speech Transcripts track.  ...  This paper describes UPC's participation in the CLEF 2007 Question Answering on Speech Transcripts track.  ... 
doi:10.1007/978-3-540-85760-0_56 fatcat:teobynnqsvcrxdbm3vcsc6xz5u

Robust Question Answering for Speech Transcripts: UPC Experience in QAst 2008 [chapter]

Pere R. Comas, Jordi Turmo
2009 Lecture Notes in Computer Science  
For the processing of manual transcripts we have deployed a robust factual Question Answering that uses minimal syntactic information.  ...  This paper describes the participation of the Technical University of Catalonia in the CLEF 2008 Question Answering on Speech Transcripts track.  ...  Introduction The CLEF 2008 Question Answering on Speech Transcripts (QAst) track [9] consists of five scenarios with several tasks: Question Answering (QA) in manual transcripts of recorded lectures  ... 
doi:10.1007/978-3-642-04447-2_61 fatcat:cd4qc6s7endkxp7jlr6ijgjsyi

Robust Question Answering for Speech Transcripts: UPC Experience in QAst 2009 [chapter]

Pere R. Comas, Jordi Turmo
2010 Lecture Notes in Computer Science  
For the processing of manual transcripts we have deployed a robust factual Question Answering that uses minimal syntactic information.  ...  This paper describes the participation of the Technical University of Catalonia in the CLEF 2008 Question Answering on Speech Transcripts track.  ...  Introduction The CLEF 2008 Question Answering on Speech Transcripts (QAst) track [9] consists of five scenarios with several tasks: Question Answering (QA) in manual transcripts of recorded lectures  ... 
doi:10.1007/978-3-642-15754-7_34 fatcat:i4hs5hmcj5drhj7o2tbrwnur64

Page 717 of Linguistics and Language Behavior Abstracts: LLBA Vol. 23, Issue 2 [page]

1989 Linguistics and Language Behavior Abstracts: LLBA  
; 8903482 Text Segmentation for Speech, Brown Corpus analysis; word class tag- ging; 8903440 Text Segmentation for Speech, English tone units; spoken discourse, segmentation rules; 8903479 Text Segmentation  ...  ; word role; 8903476 question-answer program, user’s domain knowledge effect; part-/ process-oriented descriptive strategies proposed; TAILOR computer system implemented; 8903467 Russian ellipsis/null  ... 

SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks [article]

Stefan Wermter, Volker Weber
1997 arXiv   pre-print
A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels.  ...  In this paper, we focus on a detailed description of SCREEN's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the  ...  Furthermore, we use transcripts of spontaneous language for training in the domain of meeting arrangements. Most utterances are questions and answers about dates and locations.  ... 
arXiv:cmp-lg/9702001v1 fatcat:eiamo7gybrhoxg2gfczpbydwte

SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks

S. Wermter, V. Weber
1997 The Journal of Artificial Intelligence Research  
A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels.  ...  In this paper, we focus on a detailed description of SCREEN's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the  ...  Furthermore, we use transcripts of spontaneous language for training in the domain of meeting arrangements. Most utterances are questions and answers about dates and locations.  ... 
doi:10.1613/jair.282 fatcat:rogcszyhtjfl5p3h4qrtb3zjb4

Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords [article]

Prashanth Gurunath Shivakumar, Panayiotis Georgiou, Shrikanth Narayanan
2021 arXiv   pre-print
The usefulness of the proposed Confusion2vec representation is evaluated using semantic, syntactic and acoustic analogy and word similarity tasks.  ...  We demonstrate that Confusion2vec subword modeling eliminates the need for retraining/adapting the natural language understanding models on ASR transcripts.  ...  The Acoustic analogy task comprises of word pair analogies compiled using homophones which answer questions of the form: W 1 sounds similar to W 2 as W 3 sounds similar to W 4 .  ... 
arXiv:2102.02270v2 fatcat:vub2jezhwffetbriizz5ftctci

Quantified language connectedness in schizophrenia-spectrum disorders

AE Voppel, JN de Boer, SG Brederoo, HG Schnack, IEC Sommer
2021 Psychiatry Research  
Mean, minimal and variance of similarity were calculated per window size and used in a random forest classifier to distinguish patients and healthy controls.  ...  Using a semi-structured interview, speech of 50 patients with a schizophrenia-spectrum disorder and 50 controls was recorded.  ...  Acknowledgements The authors are grateful to all participants and wish to thank all research interns for their help with data collection and preparation.  ... 
doi:10.1016/j.psychres.2021.114130 pmid:34332431 fatcat:o55lefzk3fespojgapfucb5sy4

Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning

Gabriel Marzinotto, Géraldine Damnati, Frédéric Béchet
2019 Interspeech 2019  
robustness to lexical and stylistic variations as well as automatic speech recognition errors.  ...  The underlying question throughout this study is whether adversarial learning can be used to combine data from different sources and train models on a higher level of abstraction in order to increase their  ...  [9] and the introduction of multi-task learning to jointly handle syntactic and semantic analysis [10] .  ... 
doi:10.21437/interspeech.2019-2732 dblp:conf/interspeech/MarzinottoDB19 fatcat:vk3dl44zxnf3tejbmomoxilfc4

Reranked aligners for interactive transcript correction

Benoit Favre, Mickael Rouvier, Frederic Bechet
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
ASR errors that might harm the alignment are addressed through phonetic matching, and a word embedding distance is used to account for the use of synonyms outside targeted segments.  ...  We propose to use variants of Levenshtein alignment for merging an errorful utterance with a targeted rephrase of an error segment.  ...  The merger processes the answers to clarification questions to produce a better transcript before translation.  ... 
doi:10.1109/icassp.2014.6853575 dblp:conf/icassp/FavreRB14 fatcat:jkp3zacqlngsthb7frg44xdhom

The Role of Fundamental Frequency and Temporal Envelope in Processing Sentences with Temporary Syntactic Ambiguities

Victoria Sharpe, Daniel Fogerty, Dirk-Bart den Ouden
2016 Language and Speech  
Previous experiments have demonstrated the impact of speech prosody on syntactic processing.  ...  The present study was designed to examine how listeners use specific acoustic properties of prosody for grammatical interpretation.  ...  For sentence (2a), participants would be asked "Did Mary bathe the baby?". All questions corresponding to GP sentences had a correct answer of "NO," due to the syntactic structure.  ... 
doi:10.1177/0023830916652649 pmid:28915784 fatcat:2qh45kzh6jasfbxjyhcnxnf2si

A Robust System for Natural Spoken Dialogue [article]

James F. Allen, Bradford W. Miller, Eric K. Ringger, Teresa Sikorski
1996 arXiv   pre-print
Robustness is achieved by a combination of statistical error post-correction, syntactically- and semantically-driven robust parsing, and extensive use of the dialogue context.  ...  It specifically addresses the issue of robust interpretation of speech in the presence of recognition errors.  ...  Many thanks to Alex Rudnicky, Ronald Rosenfeld and Sunil Issar at CMU for providing the Sphinx-II system and related tools.  ... 
arXiv:cmp-lg/9606023v1 fatcat:tahoou6wircxnooyj57ch67g7m

The effects of processing and sequence organization on the timing of turn taking: a corpus study

Seán G. Roberts, Francisco Torreira, Stephen C. Levinson
2015 Frontiers in Psychology  
We use the Switchboard corpus of English telephone conversation, already richly annotated for syntactic structure speech act sequences, and segmental alignment.  ...  An alternative view comes from the field of conversation analysis, which predicts that the rules of turn-taking and sequence organization may dictate the variation in gap durations (e.g., the functional  ...  We thank the Max Planck Society for additional support.  ... 
doi:10.3389/fpsyg.2015.00509 pmid:26029125 pmcid:PMC4429583 fatcat:humkxc3wlrhujg6gixi3o5gd3a

Prediction of psychosis across protocols and risk cohorts using automated language analysis

Cheryl M. Corcoran, Facundo Carrillo, Diego Fernández-Slezak, Gillinder Bedi, Casimir Klim, Daniel C. Javitt, Carrie E. Bearden, Guillermo A. Cecchi
2018 World Psychiatry  
Bearden et al 8 applied manually coded linguistic analyses to brief speech transcripts in a CHR cohort, finding that both semantic features (illogical thinking) and reduction in syntactic complexity (poverty  ...  More broadly, automated linguistic analysis can be a powerful tool for diagnosis and treatment across neuropsychiatry.  ...  to submit the manuscript for publication.  ... 
doi:10.1002/wps.20491 pmid:29352548 pmcid:PMC5775133 fatcat:splhzfldnvhlzncx3k66sldhly

A robust system for natural spoken dialogue

James F. Allen, Bradford W. Miller, Eric K. Ringger, Teresa Sikorski
1996 Proceedings of the 34th annual meeting on Association for Computational Linguistics -  
Robustness is achieved by a combination of statistical error post-correction, syntactically-and semantically-driven robust parsing, and extensive use of the dialogue context.  ...  It specifically addresses the issue of robust interpretation of speech in the presence of recognition errors.  ...  Many thanks to Alex Rudnicky, Ronald Rosenfeld and Sunil Issar at CMU for providing the Sphinx-II system and related tools.  ... 
doi:10.3115/981863.981872 dblp:conf/acl/AllenMRS96 fatcat:ue7dybxtazfghirxb6lw5obfwi
« Previous Showing results 1 — 15 out of 3,040 results