搜索结果: 1-15 共查到“计算语言学 recognition”相关记录18条 . 查询时间(0.109 秒)
Chinese Word Segmentation and Named Entity Recognition:A Pragmatic Approach
Chinese Word Segmentation Named Entity Recognition Pragmatic Approach
2015/8/31
This article presents a pragmatic approach to Chinese word segmentation. It differs from most previous approaches mainly in three respects. First, while theoretical linguists have defined Chinese word...
Unsupervised Named Entity Recognition Using Syntactic and Semantic Contextual Evidence
Unsupervised Named Entity Recognition Syntactic Semantic Contextual
2015/8/26
Proper nouns form an open class, making the incompleteness of manually or automatically learned classification rules an obvious problem. The purpose of this paper is twofold: first, to suggest the use...
Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
Dialogue Act Modeling Automatic Tagging Recognition of Conversational Speech
2015/8/25
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as STATEMENT, Question, BACKCHANNEL, Agreement, Disagreement, and Apology. Our ...
Speech and Language Processing:An Introduction to Natural Language Processing,Computational Linguistics,and Speech Recognition
Speech and Language Processing Introduction to Natural Language Processing Computational Linguistics Speech Recognition
2015/8/25
Jurafsky and Martin’s long-awaited text sets a new gold standard that will be difficult to surpass, as attested by the flurry of glowing reviews that accompanied its publication early this year.1 In a...
Visual word recognition and pronunciation:A computational model of acquisition,skilled performance,and dyslexia
Visual word recognition and pronunciation computational model of acquisition skilled performance dyslexia
2015/6/19
Visual word recognition and pronunciation:A computational model of acquisition,skilled performance,and dyslexia.
Named Entity Recognition with Character-Level Models
Named Entity Recognition Character-Level Models
2015/6/12
We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level ...
An Effective Two-Stage Model for Exploiting Non-Local Dependencies in Named Entity Recognition
Two-Stage Model Non-Local Dependencies Named Entity Recognition
2015/6/12
This paper shows that a simple two-stage approach to handle non-local dependencies in Named Entity Recognition (NER) can outperform existing approaches that handle non-local dependencies, while being ...
Many named entities contain other named entities inside them. Despite this fact, the field of named entity recognition has almost entirely ignored nested named entity recognition, but due to technolog...
Speech Recognition without a Lexicon - Bridging the Gap between Graphemic and Phonetic Systems
lexicon learning pronunciation modeling
2014/11/27
Modern speech recognizers rely on three core components: an acoustic model, a language model, and a pronunciation lexicon. In order to expand speech recognition capability to lowresource languages and...
Updated MINDS Report on Speech Recognition and Understanding, Part 2
Updated MINDS Report Speech Recognition Understanding
2014/11/27
This article is the second partof an updated version of the“MINDS 2006–2007 Reportof the Speech UnderstandingWorking Group,” one of five reports emanating from two workshops entitled “Meeting of the M...
DISCRIMINATIVE TRAINING OF HIERARCHICAL ACOUSTIC MODELS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
hierarchical acoustic modeling discriminative training LVCSR
2014/11/27
In this paper we propose discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition tasks. After presenting our hierarchical modeling framework, we desc...
FLEXIBLE MULTI-STREAM FRAMEWORK FOR SPEECH RECOGNITION USING MULTI-TAPE FINITE-STATE TRANSDUCERS
FLEXIBLE MULTI-STREAM FRAMEWORK SPEECH RECOGNITION MULTI-TAPE FINITE-STATE TRANSDUCERS
2014/11/27
We present an approach to general multi-stream recognition utilizing multi-tape finite-state transducers (FSTs). The approach is novel in that each of the multiple “streams” of features can represent ...
PRODUCTION DOMAIN MODELING OF PRONUNCIATION FOR VISUAL SPEECH RECOGNITION
PRODUCTION DOMAIN MODELING PRONUNCIATION VISUAL SPEECH RECOGNITION
2014/11/27
Articulatory feature models have been proposed in the automatic speech recognition community as an alternative to phone-based models ofspeech. In this paper, we extend this approach to the visual moda...
A probabilistic framework for segment-base d speech recognition
probabilistic framework segment-based speech recognition
2014/11/27
Most current speech recognizers use an observation space based on a temporal sequence of measurements extracted from fixed-length ‘‘frames’’ (e.g., Mel-cepstra). Given a hypothetical word or sub-word ...
BAUM-WELCH TRAINING FOR SEGMENT-BASED SPEECH RECOGNITION
BAUM-WELCH TRAINING SEGMENT-BASED SPEECH RECOGNITION.
2014/11/27
BAUM-WELCH TRAINING FOR SEGMENT-BASED SPEECH RECOGNITION.