Filters








941 Hits in 6.5 sec

Semantic understanding by combining extended CFG parser with HMM model

Yushi Xu, Stephanie Seneff, Alice Li, Joe Polifroni
2010 2010 IEEE Spoken Language Technology Workshop  
This paper presents a method for extracting both syntactic and semantic tags.  ...  Four experiments and applications were performed using the paradigm to show the usefulness of the approach in processing spoken sentences.  ...  The parser is fast, small-foot-print, and robust to spoken language characteristics.  ... 
doi:10.1109/slt.2010.5700824 dblp:conf/slt/XuSLP10 fatcat:wshaoz3gvzfsjiqcmknjysb2eq

Using key part-of-speech analysis to examine spoken discourse by Taiwanese EFL learners

Yen-Liang Lin
2014 ReCALL  
Specifically, it reveals the lexical and grammatical categories that occur unusually frequently or unusually infrequently in the English learners' discourse when compared with the language used by the  ...  The key word method extended to a part-of-speech level using the web-based corpus analytical tool,Wmatrix, highlights those linguistic domains which deserve particular attention.  ...  Corpus Since this study aims to examine the particular linguistic features of spoken communication, an analysis based on naturally occurring samples of language data is necessary.  ... 
doi:10.1017/s0958344014000408 fatcat:lvo5z2quifekdknwikfyufsnea

Chinese Utterance Segmentation in Spoken Language Translation [chapter]

Chengqing Zong, Fuji Ren
2003 Lecture Notes in Computer Science  
This paper presents an approach to segmenting Chinese utterances for a spoken language translation (SLT) system in which Chinese speech is the source input.  ...  supplement to the function of sentence boundary detection in speech recognition, in order to identify the boundaries of simple sentences and fixed expressions within the speech recognition results of a Chinese  ...  Mark Seligman for his very useful suggestions and his very careful proofreading. The authors also thank the anonymous reviewers for their helpful comments.  ... 
doi:10.1007/3-540-36456-0_55 fatcat:icdv47ashreutpzjeaqzfrcm5y

A 43 Language Multilingual Punctuation Prediction Neural Network Model

Xinxing Li, Edward Lin
2020 Interspeech 2020  
We also show that the shared information can help in fine-tuning for low-resource languages as well.  ...  languages.  ...  Compared with only using lexical features, CRF model shows great improvement combining 1 43 languages: Afrikaans, Armenian, Catalan, Chinese (Simplified, Traditional), Croatian, Czech, Danish, Dutch, English  ... 
doi:10.21437/interspeech.2020-2052 dblp:conf/interspeech/LiL20b fatcat:3pdzf6qyv5eyddnxm77t2iggyi

A maximum-entropy chinese parser augmented by transformation-based learning

Pascale Fung, Grace Ngai, Yongsheng Yang, Benfeng Chen
2004 ACM Transactions on Asian Language Information Processing  
We augment an existing maximum entropy parser with transformation-based learning, creating a parser that can operate at the character level.  ...  Many natural language applications such as spoken-language understanding, machine translation, and information extraction, would benefit from, or even require, high accuracy parsing as a preprocessing  ...  ACKNOWLEDGMENTS The authors would also like to thank Radu Florian at IBM Research for providing the rule templates used by the transformation-based word segmenter and POS tagger.  ... 
doi:10.1145/1034780.1034786 fatcat:i6ouvxugqzbsxoevdtmwm3axca

MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System

Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey Sorensen, Michael Picheny
2002 Machine Translation  
MARS is aimed at two-way conversational spoken language translation between English and Mandarin Chinese for limited domains, such as air travel reservations.  ...  Many new features and innovations have been incorporated into MARS: the translation is based on understanding the meaning of the sentence; the semantic parser uses a statistical model and is trained from  ...  Special thanks to our colleague Jeff Kuo for proofreading our manuscript. Notes  ... 
doi:10.1023/b:coat.0000010802.38267.29 fatcat:6wjmgrzi7famlojqzy3vuogncm

Survey of Named Entity Recognition Systems with respect to Indian and Foreign Languages

Nita Patil, Ajay S., B. V.
2016 International Journal of Computer Applications  
The study and observations related to approaches, techniques and features required to implement NER for various languages especially for Indian languages is reported.  ...  This paper presents a survey regarding NER research done for various Indian and non Indian languages.  ...  Wu et.al. designed a Chinese Name Entity tagger using character based model since Chinese words do not contain space and every character is meaningful.  ... 
doi:10.5120/ijca2016908197 fatcat:zxx2hsz2n5axzg2tmfluwgrhai

Table of Contents

2021 IEEE/ACM Transactions on Audio Speech and Language Processing  
Kim, Regularized Phrase-Based Topic Model for Automatic Question Classification With Domain-Agnostic Class Labels . ...Tatinati Multi-Task Sequence Tagging for Emotion-Cause Pair Extraction Via Tag Distribution  ...  Zhou Knowing Where to Leverage: Context-Aware Graph Convolutional Network With an Adaptive Fusion Layer for Contextual Spoken Language Understanding . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/taslp.2021.3137066 fatcat:ocit27xwlbagtjdyc652yws4xa

Table of Contents [EDICS]

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Liu 2438 Machine Translation for Spoken and Written Language Neural Machine Translation With Noisy Lexical Constraints . . . . . . . . . . . . . . . . . . . . . H. Li, G. Huang, D. Cai, and L.  ...  Huang 1198 Word-Character Graph Convolution Network for Chinese Named Entity Recognition . . . . . Z. Tang, B. Wan, and L.  ... 
doi:10.1109/taslp.2020.3046150 fatcat:easrxuwl6zdppejsrf4bskxfw4

Data-to-Text Generation with Iterative Text Editing [article]

Zdeněk Kasner, Ondřej Dušek
2021 arXiv   pre-print
The output of the model is filtered by a simple heuristic and reranked with an off-the-shelf pre-trained language model.  ...  Furthermore, we show that our formulation of data-to-text generation opens up the possibility for zero-shot domain adaptation using a general-domain dataset for sentence fusion.  ...  Acknowledgements We would like to thank the anonymous reviewers for the relevant comments.  ... 
arXiv:2011.01694v2 fatcat:ttuhfzvgcvhnvfd33jff5mehb4

An Autosegmental-Metrical Analysis and Prosodic Annotation Conventions for Cantonese* [chapter]

Wai Yi P. Wong, Marjorie K. M. Chan, Mary E. Beckman
2005 Prosodic Typology  
We also thank Sun-Ah Jun and an anonymous reviewer for providing us with thoughtful suggestions and comments.  ...  ACKNOWLEDGEMENTS We thank Steve Cassidy and Jonathan Harrington of the Speech and Hearing Research Centre at Macquarie University for advice in the implementation of the EMU speech database labelling  ...  In an Emu-based transcription, elements on this level are defined as "segments" (i.e. tags for discrete intervals with both a beginning and end) rather than as "events" (tags which are associated with  ... 
doi:10.1093/acprof:oso/9780199249633.003.0010 fatcat:yki5ec2xdbfujlrqa6io3apsza

Speech segmentation and spoken document processing

M. Ostendorf, B. Favre, R. Grishman, D. Hakkani-Tur, M. Harper, D. Hillard, J. Hirschberg, Heng Ji, J.G. Kahn, Yang Liu, S. Maskey, E. Matusov (+5 others)
2008 IEEE Signal Processing Magazine  
A key challenge in moving from text-based documents to such "spoken documents" is that spoken language lacks explicit punctuation and formatting, which can be crucial for good performance.  ...  P rogress in both speech and language processing has spurred efforts to support applications that rely on spoken-rather than written-language input.  ...  POS tagging and parsing, which are well studied and useful techniques for processing text, are now being applied to spoken language transcripts.  ... 
doi:10.1109/msp.2008.918023 fatcat:jrry5lad2nbjpfd36vncqfyila

Table of Contents

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Chen 1183 Out-of-Domain Detection for Natural Language Understanding in Dialog Systems . , and R. M.  ...  Wang 2109 (Contents Continued on Page vi) 671 Maximal Figure-of-Merit Framework to Detect Multi-Label Phonetic Features for Spoken Language 852 Cognitive-Driven Binaural Beamforming Using EEG-Based  ... 
doi:10.1109/taslp.2020.3046148 fatcat:hirdphjf6zeqdjzwnwlwlamtb4

Speech act classification in Vietnamese Utterance and its application in smart mobile voice interaction

Thi-Lan Ngo, Quang-Vu Duong, Son-Bao Pham, Xuan-Hieu Phan
2016 Proceedings of the Seventh Symposium on Information and Communication Technology - SoICT '16  
Automatic speech act classification has been studied in many languages such as English, Chinese, Slovakian, Arabic, but not yet in Vietnamese.  ...  The experiment result has demonstrated the ability of this classifier such as robust, compact and can work well on mobiles.  ...  Nguyen-Son Vo for helpful comments.  ... 
doi:10.1145/3011077.3011119 dblp:conf/soict/NgoDPP16 fatcat:jijf7p67vjdntasbxnk6l5ejty

Pinyin Spelling Promotes Reading Abilities of Adolescents Learning Chinese as a Foreign Language: Evidence From Mediation Models

Huimin Xiao, Caihua Xu, Hetty Rusamy
2020 Frontiers in Psychology  
Pinyin spelling skills were assessed by two measures, Pinyin Dictation (sentence dictation in Pinyin) and Pinyin Tagging (Pinyin writing for characters).  ...  The present study examined the role of Pinyin spelling in the reading abilities of adolescents learning Chinese as a foreign language (CFL).  ...  Pinyin Tagging (Pinyin writing for characters).  ... 
doi:10.3389/fpsyg.2020.596680 pmid:33362659 pmcid:PMC7757380 fatcat:e6adxigit5ftvcvazdla54aiii
« Previous Showing results 1 — 15 out of 941 results