搜索结果: 1-15 共查到“应用语言学 Unsupervised”相关记录17条 . 查询时间(0.089 秒)
Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning
Semi-Supervised Unsupervised Learning
2017/4/6
Highly frequent in language and communication, metaphor represents a significant challenge
for Natural Language Processing (NLP) applications. Computational work on metaphor has
traditionally evolve...
This article proposes ESA, a new unsupervised approach to word segmentation. ESA is an iterative process consisting of 3 phases: Evaluation, Selection, and Adjustment. In Evaluation, both certainty an...
Unsupervised Type and Token Identification of Idiomatic Expressions
Unsupervised Type Token Identification Idiomatic Expressions
2015/9/7
Idiomatic expressions are plentiful in everyday language, yet they remain mysterious, as it is not clear exactly how people learn and understand them. They are of special interest to linguists, psycho...
There has been a great deal of recent research into word sense disambiguation, particularly since the inception of the Senseval evaluation exercises. Because a word often has more than one meaning, re...
Unsupervised Multilingual Sentence Boundary Detection
Unsupervised Multilingual Sentence Boundary Detection
2015/9/1
In this article, we present a language-independent, unsupervised approach to sentence boundary detection. It is based on the assumption that a large number of ambiguities in the determination of sente...
Unsupervised Learning of the Morphology of a Natural Language
Unsupervised Learning Natural Language
2015/8/26
This study reports the results of using minimum description length (MDL) analysis to model unsupervised learning of the morphological segmentation of European languages, using corpora ranging in size ...
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...
Modeling Unsupervised Perceptual Category Learning
human learning mixture of Gaussians online learning unsupervised learning
2015/6/23
During the learning of speech sounds and other perceptual categories, category labels are not provided, the number of categories is unknown, and the stimuli are encountered sequentially. These constra...
Unsupervised Learning of Field Segmentation Models for Information Extraction
Unsupervised Learning Field Segmentation Models Information Extraction
2015/6/12
The applicability of many current information extraction techniques is severely limited by the need for supervised training data. We demonstrate that for certain field structured extraction tasks, suc...
Unsupervised morphological analysis of small corpora: First experiments with Kilivila
Unsupervised morphological analysis small corpora First experiments with Kilivila
2015/4/21
Language documentation involves linguistic analysis of the collected material, which is typically done manually. Automatic methods for language processing usually require large corpora. The method pre...
The development of an automatic speech recognizer is typically a highly supervised process involving the specification of phonetic inventories, lexicons, acoustic and language models, and requiring an...
HANDLING UNCERTAIN OBSERVATIONS IN UNSUPERVISED TOPIC-MIXTURE LANGUAGE MODEL ADAPTATION
language model latent topic model topic tracking confusion network
2014/11/27
We propose an extension to the recent approaches in topic-mixture modeling such as Latent Dirichlet Allocation and Topic Tracking Model for the purpose of unsupervised adaptation in speech recognition...
Unsupervised Speaker Adaptation based on the Cosine Similarity for Text-Independent Speaker Verification
Unsupervised Speaker Adaptation Cosine Similarity Text-Independent Speaker Verification
2014/11/27
This paper proposes a new approach to unsupervised speaker adaptation inspired by the recent success of the factor analysisbased Total Variability Approach to text-independent speaker verification [1]...
TOWARDS MULTI-SPEAKER UNSUPERVISED SPEECH PATTERN DISCOVERY
unsupervised learning language acquisition
2014/11/27
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach provides significant...
We present an unsupervised algorithm f or discovering acoustic patterns i n s peech by finding matching subsequences between pairs of utterances. T he approach we describe is, in theory, language and ...