搜索结果: 1-6 共查到“文学 Statistical Parsing”相关记录6条 . 查询时间(0.156 秒)
A Statistical Parsing Framework for Sentiment Classification
Statistical Parsing Framework Sentiment Classification
font style='font-size:12px;'>
2015/9/15
We present a statistical parsing framework for sentence-level sentiment classification in this article. Unlike previous works that use syntactic parsing results for sentiment analysis, we develop a st...
Wide-Coverage Deep Statistical Parsing Using Automatic Dependency Structure Annotation
Wide-Coverage Deep Statistical Parsing Automatic Dependency Structure Annotation
font style='font-size:12px;'>
2015/9/6
A number of researchers have recently conducted experiments comparing “deep” hand-crafted wide-coverage with “shallow” treebank- and machine-learning-based parsers at the level of dependencies, using ...
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models
Wide-Coverage Statistical Parsing CCG Log-Linear Models
font style='font-size:12px;'>
2015/9/2
This article describes a number of log-linear parsing models for an automatically extracted lexicalized grammar. The models are “full” parsing models in the sense that probabilities are defined for co...
Sample Selection for Statistical Parsing
Sample Selection Statistical Parsing
font style='font-size:12px;'>
2015/8/31
Corpus-based statistical parsing relies on using large quantities of annotated text as training examples. Building this kind of resource is expensive and labor-intensive. This work proposes to use sam...
Optimizing Local Probability Models for Statistical Parsing
Local Probability Models Statistical Parsing
font style='font-size:12px;'>
2015/6/12
This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems — history-based generative parsi...
An Information-Theory-Based Feature Type Analysis for the Modelling of Statistical Parsing
Information-Theory-Based Feature Type Statistical Parsing
font style='font-size:12px;'>
2009/2/13
The paper proposes an information-theory-based method for feature types analysis in probabilistic evaluation modelling for statistical parsing. The basic idea is that we use entropy and conditional en...