Gigaword & Dialog Systems


See also:

Dialog Systems | Linguistic Data Consortium & Dialog Systems


Recognizing entailment in intelligent tutoring systems. RD Nielsen, W Ward, JH Martin – Natural Language …, 2009 – Cambridge Univ Press … Rather than use the web as our corpus (as did Turney (2001) and Glickman et al. (2005), who generate analogous similarity statistics), we use three publicly available corpora (English Gigaword, The Reuters corpus, and Tipster) totaling 7.4 M articles and 2.6 B indexed terms. … Cited by 21 Related articles All 18 versions Cite

More data and tools for more languages and research areas: a progress report on LDC activities C Cieri, M Liberman – 5th International Conference on …, 2006 – gandalf.aksis.uib.no … During that same time, LDC has added two titles to the catalog to support the development of dialogue systems: the 2000 and 2001 Communicator Dialogue Act … Gigaword corpora targeting an order of magnitude of a billion words or a billion Chinese characters of news text. … Cited by 4 Related articles All 7 versions Cite

A Progress Report from the Linguistic Data Consortium: Recent Activities in Resource Creation and Distribution and the Development of Tools and Standards. C Cieri, M Liberman – LREC, 2004 – hnk.ffzg.hr … Language Modeling: Gigaword News text … Voicemail Corpus Part II, HUB5 English, Egyptian Arabic, English, German, Mandarin, Spanish, CallHome style telephone conversation audio, transcripts and lexicon in Egyptian Arabic and Korean • Dialog Systems: 2002 and 2001 … Cited by 1 Related articles All 9 versions Cite

Open Dialogue Management for Relational Databases B Hixon, RJ Passonneau – Proceedings of NAACL-HLT, 2013 – newdesign.aclweb.org … Here, we use simula- tion to exercise each dialogue system with a large number of cases in … in a subset of the New York Times portion of the English Gigaword corpus (Parker … knows a particular value is the normalized fre- quency that the attribute’s values appear in Giga- word. … Related articles All 7 versions Cite

Combined low level and high level features for out-of-vocabulary word detection. B Lecouteux, G Linarès, B Favre – INTERSPEECH, 2009 – icsi.berkeley.edu … These methods obtain better accuracy than the filler- model, but they are limited to spoken dialog systems or isolated word recognition. Moreover, they do not use robust linguistic features. … This filter combines two measures based on the web and the French Gigaword corpus. … Cited by 13 Related articles All 10 versions Cite

Language model adaptation for tiny adaptation corpora. D Klakow – INTERSPEECH, 2006 – 20.210-193-52.unknown.qala.com. … … For the development of transcription systems as well as dialogue systems this curve captures the trade-off of performance versus effort for data collection … Future work will use a much large background corpus, pos- sibly the gigaword corpus and also investigate in more detail the … Cited by 10 Related articles All 4 versions Cite

Using a Probabilistic Model of Context to Detect Word Obfuscation. S Jabbari, B Allison, L Guthrie – LREC, 2008 – repository.dlsi.ua.es … In lan- guage generation for dialog systems, in order to create a natural dialogue, a paraphrase generator … In this work, we derive the relevant counts from the English Giga- word, a 1.5 billion … We use 1.4 billion words of English Gigaword v.1, a newswire corpus collected from … Cited by 4 Related articles All 7 versions Cite

Optimizing sentence segmentation for spoken language translation. S Rao, IR Lane, T Schultz – INTERSPEECH, 2007 – cs.cmu.edu … applications include among others Spoken Language Translation systems (SLT), speech summarization and dialog systems. … The language model was trained on the Arabic giga- word corpus with an additional … was trained on 32 million words from the Arabic gigaword corpus. … Cited by 10 Related articles All 9 versions Cite

Data driven approach for language model adaptation using stepwise relative entropy minimization A Sethy, S Narayanan… – Acoustics, Speech and …, 2007 – ieeexplore.ieee.org … Text harvested from the web combined with other large text collections such as GigaWord provides a good resource to supplement the in … our previous results on the Transonics task [8]. The Transonics sys- tem is a real-time limited domain dialog system for medical domain … Cited by 6 Related articles Cite

Modeling the dative alternation with automatically extracted features H Zhong, A Stent, M Swift – … approaches for spoken dialogue systems, 2006 – aaai.org … The Text data set comprises the fol- lowing two corpora: the APW-Dec-99 portion of the English Gigaword (GW) corpus of raw text (Graff et al. … Graff, D.; Kong, J.; Chen, K.; and Maeda, K. 2005. English gigaword second edition. ISBN: 1-58563-350-X. … Cited by 2 Related articles All 7 versions Cite

Blueprint for a high performance NLP Infrastructure JR Curran – Proceedings of the HLT-NAACL 2003 workshop on …, 2003 – dl.acm.org … greatest increase is in the amount of raw text available to be processed, eg the English Giga- word Corpus (Linguistic … There have already been several attempts to develop distributed NLP systems for dialogue systems (Bayer et al., 2001) and speech … English Gigaword Corpus. … Cited by 12 Related articles All 24 versions Cite

A hybrid model for spontaneous speech understanding T Zhang, M Hasegawa-Johnson, S Levinson – Proceedings of the AAAI …, 2005 – Citeseer … Adult users of a typical dialogue system (eg, for purchase of air travel or financial instruments) are usually able to learn, over a number … We use GigaWord, a billion-word archive of English newswire text and distributed by the Linguistic Data Consortium, as the text database for … Cited by 7 Related articles All 7 versions Cite

Syntactic surprisal affects spoken word duration in conversational contexts V Demberg, AB Sayeed, PJ Gorinski… – Proceedings of the …, 2012 – dl.acm.org … Spoken dialogue systems are of increasing eco- nomic and technological importance in recent times, particularly as it is now feasible to include this tech- nology in everything from small consumer devices to industrial equipment. … Gigaword CMU toolkit AMI word freq. … Cited by 1 Related articles All 7 versions Cite

Soft computing in intelligent tutoring systems and educational assessment RD Nielsen, W Ward, JH Martin – Soft Computing Applications in Business, 2008 – Springer Page 1. B. Prasad (Ed.): Soft Computing Applications in Business, STUDFUZZ 230, pp. 201–230, 2008. springerlink.com © Springer-Verlag Berlin Heidelberg 2008 Soft Computing in Intelligent Tutoring Systems and Educational Assessment … Cited by 2 Related articles All 3 versions Cite

Generating descriptions that summarize geospatial and temporal data M Molina, A Stent – Tools with Artificial Intelligence, 2009. ICTAI’ …, 2009 – ieeexplore.ieee.org … [8] D. Graff, “English Gigaword”, Linguistic Data Consortium Catalog No. LDC2003T05, 2003. … [14] O. Rambow, S. Bangalore, and MA Walker, “Natural language generation in dialog systems”, in Proceedings of the Human Language Technology Conference, 2001. … Cited by 1 Related articles All 5 versions Cite

Extraction of pragmatic and semantic salience from spontaneous spoken English T Zhang, M Hasegawa-Johnson, SE Levinson – Speech Communication, 2006 – Elsevier … This paper demonstrates the automatic tagging of contrast and focus for the purpose of robust spontaneous speech understanding in a tutorial dialogue system. … Spoken language understanding; Spoken dialogue systems; Computational linguistics; Information extraction. … Cited by 16 Related articles All 8 versions Cite

Grid-enabling natural language engineering by stealth B Hughes, S Bird – Proceedings of the HLT-NAACL 2003 workshop on …, 2003 – dl.acm.org … ally0intensive. Building complex applications, such as spoken dialogue systems, depends on iden0 tifying and integrating suitable components often from a range of sources. … David Graff, 2002. English Gigaword. Linguistic Data Consortium. … Cited by 18 Related articles All 3 versions Cite

Data selection for language modeling using sparse representations. A Sethy, TN Sainath… – …, 2010 – 20.210-193-52.unknown.qala.com. … … Text harvested from the web and other large text collec- tions such as the English Gigaword corpus provide a good re- source to supplement the in-domain data for a … [6] K. Weilhammer, MN Stuttlem, and S. Young, “Boot- strapping language models for dialogue systems,” in Pro … Cited by 1 Related articles All 2 versions Cite

A knowledge-based method for generating summaries of spatial movement in geographic areas M Molina, A Stent – International Journal on Artificial Intelligence …, 2010 – World Scientific … Page 14. M. Molina & A. Stent 406 language model trained on the APW section of the English Gigaword corpus.9 Examples of sentence plan rules are shown in Figure 7. The surface realizer generates text from the abstract representations for each sentence. … Cited by 6 Related articles All 5 versions Cite

August 2009 R Kuhn, P Isabelle – 2009 – mt-archive.info … MT for dialogue • (Starlander & Estrella): MedSLT is speech dialogue system for multilingual doctor-patient communication, with back translation. Grammar-based MT … the news domain by self-training on Arabic news data (from Arabic Gigaword); +3.5 BLEU. • (Dugast et al. … All 2 versions Cite

An iterative relative entropy minimization-based data selection approach for n-gram model adaptation A Sethy, PG Georgiou, B Ramabhadran… – Audio, Speech, and …, 2009 – ieeexplore.ieee.org … results on language model adaptation using two speech recogni- tion tasks: a medium vocabulary medical domain doctor-patient dialog system and a large … Text harvested from the web and other large text collections such as the English Gigaword [4] corpus provides a good re … Cited by 13 Related articles All 4 versions Cite

Spelling as a Complementary Strategy for Speech Recognition. K Vertanen, PO Kristensson – INTERSPEECH, 2012 – 20.210-193-52.unknown.qala.com. … … via multimodal correction, in some situations voice-only input is preferred, or some- times required (eg in-car appliances, telephone dialog systems, or for … Our trigram language model was trained on newswire text from the CSR-III and English Gigaword corpora (1.5B words). … Related articles All 5 versions Cite

Active Error Detection and Resolution for Speech-to-Speech Translation R Prasad, R Kumar, S Ananthakrishnan… – Proceedings IWSLT …, 2012 – hltc.cse.ust.hk … We trained this model on Gigaword, Wall Street Journal (WSJ), and TRANSTAC corpora consisting of approximately 250K utterances (4.8 M words). … of 6th LREC, 2008 [23] Turunen, M. and Hakulinen, J.“Agent-based Error Handling in Spoken Dialogue Systems”, Proc. … Cited by 3 Related articles All 5 versions Cite

Sound Environment Analysis in Smart Home MA Sehili, B Lecouteux, M Vacher, F Portet, D Istrate… – Ambient …, 2012 – Springer … To address this constraint, the dialog system developed by [8] was propo- sed to replace traditional emergency systems that requires too much change in lifestyle of … The generic LM was estimated on about 1000M of words from the French newspapers Le Monde and Gigaword. … Cited by 4 Related articles All 5 versions Cite

Experimental Evaluation of Speech Recognition Technologies for Voice-based Home Automation Control in a Smart Home M Vacher, B Lecouteux, D Istrate, T Joubert, F Portet… – aclweb.org … To ad- dress this constraint, the dialogue system developed by [6] was proposed to replace traditional emergency systems that requires too much change in the … The generic LM was estimated on about 1000M of words from the French newspapers Le Monde and Gigaword. … Cite

[BOOK] Learner answer assessment in intelligent tutoring systems RD Nielsen – 2007 – books.google.com Page 1. LEARNER ANSWER ASSESSMENT IN INTELLIGENT TUTORING SYSTEMS by RODNEY D. NIELSEN MS, University of Colorado, Boulder, 2005 A thesis submitted to the Faculty of the Graduate School of the University … Cited by 1 Related articles All 5 versions Cite

An Affect-based Approach for QoE evaluation in VoIP Systems A Bhattacharya, Z Yang, D Pan – users.cis.fiu.edu … An automatic dialog system is reported in [11] which has the ability of responding to callers according to the detected emotional state or … We create a 3-gram language model provided in a 1200 million English Gigaword corpus [2] indexed within the Linguistic Data Consortium … Related articles Cite

Evaluating semantic evaluations: How rte measures up S Bayer, J Burger, L Ferro, J Henderson… – Machine Learning …, 2006 – Springer … A team of three judges tagged approximately 900 randomly selected Giga- word documents, including 520 from Xinhua. This larger tagging effort showed that an estimated 70% of the XIE headlines in Gigaword are entailed by the cor- responding lead paragraph. … Cited by 1 Related articles All 5 versions Cite

Automatic speech recognition in the diagnosis of primary progressive aphasia K Fraser, F Rudzicz, N Graham, E Rochon – slpat.org … Simulated ASR errors have been used in various con- texts, such as training dialogue systems [2] and for testing the safety of dictation systems for … In this set of experiments, we use a language model ob- tained from the Gigaword corpus [32], since the Nuance lan- guage model … Cite

Joint Parsing and Disfluency Detection in Linear Time MS Rasooli, J Tetreault, CA Sunnyvale – cs.columbia.edu … 2011) improve the performance of TAG model by adding external language model- ing information from data sets such as Gigaword in addition to … Such a parser is useful for spo- ken dialogue systems which typically encounter disfluent speech and require accurate syntactic … Cite

A Statistical Model of Error Correction for Computer Assisted Language Learning Systems H Basiron – 2012 – otago.ourarchive.ac.nz Page 1. A Statistical Model of Error Correction for Computer Assisted Language Learning Systems Halizah Basiron a thesis submitted for the degree of Doctor of Philosophy at the University of Otago, Dunedin, New Zealand. May 24, 2012 Page 2. Abstract … Related articles Cite

System combination for machine translation of spoken and written language E Matusov, G Leusch, RE Banchs… – Audio, Speech, and …, 2008 – ieeexplore.ieee.org Page 1. 1222 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 16, NO. 7, SEPTEMBER 2008 System Combination for Machine Translation of Spoken and Written Language Evgeny Matusov … Cited by 40 Related articles All 10 versions Cite

Structural features for predicting the linguistic quality of text A Nenkova, J Chae, A Louis, E Pitler – Empirical methods in natural …, 2010 – Springer … We built unigram, bigram, and trigram language models with Good-Turing smoothing over the New York Times section of the English GigaWord corpus (over 900 million words). We used the SRI Language Modeling Toolkit [45] for this purpose. … Cited by 10 Related articles All 5 versions Cite

Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system S Matsoukas, JL Gauvain, G Adda… – Audio, Speech, and …, 2006 – ieeexplore.ieee.org … The BN LM training consisted of approximately 1 billion words of text, including the American English GigaWord News corpus, commercial transcripts from PSMedia, and CNN web archived transcripts.1 Several test sets were used to evaluate system performance during the … Cited by 35 Related articles All 13 versions Cite

Successful Conclusion of the 2010 Summer Workshop J Du – old-site.clsp.jhu.edu … In both cases, we will use a 4-gram language model trained with English Gigaword corpora along with appropriately … of more controllable emotion speech synthesis is necessary in the improvement of human machine communication in spoken dialog systems, speech to speech … Related articles All 2 versions Cite

The design of a corpus of contemporary Arabic L Al-Sulaiti, ES Atwell – International Journal of Corpus …, 2006 – ingentaconnect.com … language corpora have been used in development of English language teaching materials, as well as language processing systems such as speech recognisers, spelling and grammar checkers, dialogue systems etc. … Arabic Gigaword (2002) University of Pennsylvania LDC … Cited by 47 Related articles All 13 versions Cite

[BOOK] Verbal Irony: Theories and Automatic Detection M Fell – 2012 – books.google.com … 10 2.5 Discussion . . . . . 11 3 Automatic detection of irony 13 3.1 “Yeah Right”: Sarcasm Recognition for Spoken Dialogue Systems . . . . . 13 3.1.1 Material . . . . . 13 3.1.2 Method . . . . . … Related articles All 3 versions Cite

Linguistic Resources, Development, and Evaluation of Text and Speech Systems C Cieri – Evaluation of Text and Speech Systems, 2007 – Springer … These in- clude Gigaword News Text Corpora in English, Chinese, and Arabic [ISBN: 1-58563-271-6, 1 … information retrieval, information extraction, summarization, natural language processing, machine translation and speech-to-speech translation, and dialogue systems. … Related articles All 4 versions Cite

Grid-based indexing of a newswire corpus B Hughes, S Venugopal… – Grid Computing, 2004. …, 2004 – ieeexplore.ieee.org … Building complex applications, such as spoken dialogue systems, de- pends on identifying and integrating suitable components often from a range of sources. … LDC English Gigaword Corpus Source Files Mb-gzip Mb M-words M-docs afe 44 417 1,216 171 .656 apw 91 1,213 … Cited by 12 Related articles All 18 versions Cite

Geographical Information Resolution and its Application to the Question Answering Systems [Thesis] DF Domenech, HR Hontoria – Citeseer … simple rules that detected important words in the person’s input. GUS was a dialog system for airline reservation. … Human-Machine interaction is done by dialog systems that allow to do ques- tions in the context of previous interactions. … Related articles All 2 versions Cite

Identifying implicit relationships J Chu-Carroll, EW Brown, A Lally… – IBM Journal of …, 2012 – ieeexplore.ieee.org … To support spreading activation in Watson, we built a 5-gram corpus with frequency counts from Watson’s primary unstructured sources [6], which include Wikipedia and the Gigaword corpus [7]. All 5 grams were stemmed, and stop words were removed. … Cited by 7 Related articles All 3 versions Cite

Détection de mots hors-vocabulaire par combinaison de mesures de confiance de haut et bas niveaux B Lecouteux, G Linarès, B Favre – MajecSTIC’09 – majecstic2009.univ-avignon.fr … Elle est uniquement appliquée sur les mots détectés comme un dernier processus de filtrage. Ce filtre combine deux mesures basées sur le Web et le corpus Français Gigaword. … Se- mantic processing of out-of-vocabulary words in a spoken dialogue system. … Related articles All 2 versions Cite

A Corpus-Based Readability Formula for Estimate of Arabic Texts Reading Difficulty NM Daud, H Hassan, NA Aziz – 2013 – idosi.org … Arabic Gigaword (2002) University of Written Around 400M Natual language Agence France Presse, … (2005) speech recognition and spoken dialogue system Page 4. 1152+9640+3+9049 19844 4961 4 4 = = 21+5430+3022+2375 10848 2712 4 4 = = … Related articles All 3 versions Cite

Advances in large vocabulary continuous speech recognition G Zweig, M Picheny – Advances in Computers, 2004 – Elsevier The development of robust, accurate and efficient speech recognition systems is critical to the widespread adoption of a large number of commercial applications. Cited by 6 Related articles All 6 versions Cite

Advances in Arabic speech transcription at IBM under the DARPA GALE program H Soltau, G Saon, B Kingsbury, HKJ Kuo… – Audio, Speech, and …, 2009 – ieeexplore.ieee.org … audio. B. Training Data for Language Modeling We used the following resources for language modeling: • transcripts of the audio data released by LDC (7 M words); • the Arabic Gigaword corpus (500 M words), • news group … Cited by 22 Related articles All 5 versions Cite

Consolidation-Based Speech Translation and Evaluation Approach H Chiori, Z Bing, S Vogel, A Waibel… – IEICE transactions on …, 2009 – search.ieice.org … We used several corpora for our language model (LM) development: Mandarin Chinese News Text (LDC95T13), TDT{2,3,4}, Xinhua News, People’s Daily and China Radio respectively are contained in the Mandarin Gigaword corpus and the HUB4 1997 acoustic training … Related articles All 5 versions Cite

Pattern learning and knowledge annotation for question answering N Schlaefer, MAP Gieselmann, IT Schaaf… – Student Research …, 2005 – Citeseer … A QA system can be deployed by any kind of system that imitates human behavior to pretend general knowledge. Examples are intelligent dialog systems or humanoid robots such as the SFB 5881, which is a household robot designed to help people in the kitchen. … Cited by 1 Related articles All 7 versions Cite

Phone lattice reconstruction for embedded language recognition in LVCSR Y Shan, Y Deng, J Liu, MT Johnson – EURASIP Journal on Audio, Speech, …, 2012 – Springer … space modeling 1 Introduction Applications such as speech-to-speech translation systems and dialogue systems often work in a multilingual environ- ment, so it is necessary to rapidly identify the language being spoken. Even … Related articles All 6 versions Cite

The subspace Gaussian mixture model—A structured model for speech recognition D Povey, L Burget, M Agarwal, P Akyazi, F Kai… – Computer Speech & …, 2011 – Elsevier … Language. Volume 25, Issue 2, April 2011, Pages 404–439. Language and speech issues in the engineering of companionable dialogue systems. The subspace Gaussian mixture model—A structured model for speech recognition. … Cited by 60 Related articles All 11 versions Cite

Speechlinks: Robust Cross-Lingual Tactical Communication Aids S Narayanan, P Georgiou – 2008 – DTIC Document … We present results on language model adaptation using two speech recognition tasks: a medium vocabulary medical domain doctor-patient dialog system and a large vocabulary transcription system for European parliament plenary speeches. … Related articles All 2 versions Cite

A cascaded approach to mention detection and chaining in arabic I Zitouni, X Luo, R Florian – Audio, Speech, and Language …, 2009 – ieeexplore.ieee.org Page 1. IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 5, JULY 2009 935 A Cascaded Approach to Mention Detection and Chaining in Arabic Imed Zitouni, Member, IEEE, Xiaoqiang Luo, and Radu Florian … Cited by 3 Related articles All 4 versions Cite

Improving Statistical Machine Translation Using Bayesian Word Alignment and Gibbs Sampling C Mermer, M Saraclar, R Sarikaya – 2013 – ieeexplore.ieee.org … for training, subsets of the AFP portion of LDC2004T17 (news from year 1998) for tuning and testing, and the AFP and Xinhua subsets of the respective Gigaword corpora (LDC2007T07 and LDC2007T40) for additional LM training. … Cited by 1 Related articles Cite

N-gram posterior probability confidence measures for statistical machine translation: an empirical study A de Gispert, G Blackwood, G Iglesias, W Byrne – Machine Translation, 2013 – Springer … verification, correction of recognition results, detection or rejection of out-of-vocabulary words, and managing the flow of control in dialogue systems. … 4-gram estimated over the English side of the parallel text and a 465M word subset of the English GigaWord Third Edition (Graff … Cited by 4 Related articles All 5 versions Cite

Automated grammatical error detection for language learners C Leacock, M Chodorow, M Gamon… – Synthesis lectures on …, 2010 – morganclaypool.com … Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 … Cited by 67 Related articles All 9 versions Cite

CSLP CORPORA AND LANGUAGE RESOURCES HC Wang, TF Zheng, J Tao – speakit.cn … speech synthesis, parallel language processing (for Chinese, English, and Japanese), information indexing, and dialogue systems.13-16 … Mandarin Telephone Transcript Data (LDC) • TREC Mandarin (LDC) • Mandarin Chinese News (LDC) • Chinese Gigawords (LDC) • Hub-5 … Cited by 1 Related articles All 5 versions Cite

Long-Answer Question Answering and Rhetorical-Semantic Relations [Thesis] SJ Blair-Goldensohn – 2007 – Citeseer … 50 xi Page 16. 3.2 RSR types, sample extraction patterns, number of unique extracted instances from the Gigaword corpus, number of training instances in our active training … 67 3.4 Overview of performance for automatic insertion of SEG topic boundaries into Gigaword corpus. … Cited by 6 Related articles All 4 versions Cite

Automatic sentence structure annotation for spoken language processing DL Hillard – 2008 – Citeseer Page 1. Automatic Sentence Structure Annotation for Spoken Language Processing Dustin Lundring Hillard A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2008 … Cited by 8 Related articles All 13 versions Cite

Shaping the Future of the Multilingual Digital Europe N Calzolari, P Baroni, N Bel, G Budin, K Choukri… – 2009 – flarenet.eu Page 1. The European Language Resources and Technologies Forum Shaping the Future of the Multilingual Digital Europe Vienna, 12 -13 February 2009 Proceedings Edited by: N. Calzolari, P. Baroni, N. Bel, G. Budin, K. Choukri … Cited by 2 Related articles All 8 versions Cite

gn and peech R A Ali – cs.cmu.edu … Pakistan. This will be achieved by developing a telephone based dialogue system consisting of an Urdu Speech Recognition system and a Text to Speech system that can interact with the health workers to answer their queries. … Related articles All 4 versions Cite

FLaReNet Forum N CALZOLARI, P BARONI, N BEL, G BUDIN… – Citeseer Page 1. 1 FLaReNet Forum The European Language Resources and Technologies Forum: Shaping the Future of the Multilingual Digital Europe Vienna, 12th and 13th February 2009 EDITED BY: N. CALZOLARI, P. BARONI … Cite

cROVER: Context-augmented Speech Recognizer based on Multi-Decoders’ Output MK Abida – 2011 – uwspace.uwaterloo.ca Page 1. cROVER: Context-augmented Speech Recognizer based on Multi-Decoders’ Output by Mohamed Kacem Abida A thesis presented to the University of Waterloo in fulfillment of the thesis requirement for the degree of Doctor of Philosophy in … Related articles All 5 versions Cite

Data-intensive text processing with MapReduce J Lin, C Dyer – Synthesis Lectures on Human Language …, 2010 – morganclaypool.com … Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 … Cited by 212 Related articles All 12 versions Cite

Distributional Phrasal Paraphrase Generation for Statistical Machine Translation Y Marton – tist.acm.org Page 1. Distributional Phrasal Paraphrase Generation for Statistical Machine Translation Yuval Marton, IBM TJ Watson Research Center Paraphrase generation has been shown useful for various natural language processing tasks, including statistical machine translation. … Related articles Cite

Automatic dialect and accent recognition and its application to speech recognition F Biadsy – 2011 – rhys.cul.columbia.edu … regional origin. It should also prove useful in telephony-based help systems, either adapt- ing the output of text-to-speech synthesis in a spoken dialogue system to produce regional speech or directing the telephone conversation to an agent whose dialect is the same as the … Cited by 6 Related articles All 5 versions Cite

Intrinsic and Extrinsic Approaches to Recognizing Textual Entailment DP der Philosophischen – 2011 – coli.uni-saarland.de … Each utterance in the interpreted version is actually implied or entailed by the utterances in the original conversation. Con- sequently, if we want to build a dialogue system, dealing with this kind of implication or entailment is one of the key challenges. Let alone there … Related articles All 2 versions Cite

ISCA Scientific Achievement Medalist 2008 C Wellekens – isca-speech.org … We also received many suggestions for future releases, among them: * More African language publications * Gigaword corpora in additional languages * More annotated data for a greater variety of uses … PhD Research Studentship in Spoken Dialogue Systems- Cambridge UK. … Related articles Cite

Integrating Recognition and Retrieval With Relevance Feedback for Spoken Term Detection H Lee, C Chen, L Lee – Audio, Speech, and Language …, 2012 – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 2 Related articles All 2 versions Cite