搜索结果: 1-15 共查到“知识库 计算语言学”相关记录1071条 . 查询时间(0.73 秒)
计算语言学是近年日益受到重视的前沿交叉学科。教育部语言文字应用研究所研究员冯志伟主要研究计算语言学、语言学流派、语料库语言学、术语学，他是我国最早从事计算语言学的学者之一，从20世纪50年代末在北京大学求学期间踏上计算语言学的学术道路，为我国计算语言学的发展作出了突出贡献。作为中国计算语言学的主要开创者和发展见证者之一，已届望九之年的冯志伟研究员仍治学不辍，为学科发展持续贡献力量。在他看来，要让下...
合并与最小化计算原则互动实现了强势最简论的解释目标，合并产生加标层级结构。本文在投射理论基础上澄清最简生成程序的最小化计算、二元合并运算、加标机制及其解释关联和限制到算式库语音式接口映射的语段线性循环性，以合并生成的功能论元结构论证了参数设置模式（多模块、表征层次以及复杂移位规则组成的复杂集合）及其习得关联（投射问题），进一步明确了最小结构距离是基本的计算（程序复杂性）问题，在调查参数设定与功能语...
本文基于最简方案与语段理论的局部性制约、多重/循环拼读机制以及强势音系语段推导，在综述先前研究基础上，重点分析句子重音计算方法和优选句法运算，阐述句子重音与焦点重音的互动以及语段韵律拼读与优选制约的交互。语段结合焦点加标的分析表明，焦点重音规则优先于句子重音规则。本文不仅论证了音系计算方法的指导原则，也遵循了语段的局部性和多重拼读（移交）。系统研究证实了在显著性参照下功能语段边界和循环拼读域在重音...
基于特征选择优化的 p、t、k 偏误自动检测研究
计算机辅助发音训练 送气辅音 优化特征选择
2017/8/22
随着二语习得需求的增加，计算机辅助发音训练成为当前研究的热点之一。我们在前期工作中基于自动语音识别方法实现了常见偏误发音的自动检测，但系统对 p、t、k 送气不足偏误检测存在错误接受率过高的问题；此外探究了嗓音起始时间(VOT)参数对提高送气偏误检测性能的作用。本文针对前期检测系统中的不足，从改变边界切分方式和优化特征选择两个方面进一步完善系统。首先，音段边界切分从人工标注改为计算机自动对齐；其次...
Sentiment Analysis: Mining Opinions, Sentiments, and Emotions
Social media online business text mining the fuzzy
2016/10/31
With the increasing development of Web 2.0, such as social media and online businesses,the need for perception of opinions, attitudes, and emotions grows rapidly. Sentiment analysis, the topic studyin...
Computational Sociolinguistics: A Survey
Language social phenomena social nature computational linguistics social dimension calculating social linguistics
2016/10/31
Language is a social phenomenon and variation is inherent to its social nature. Recently, there has been a surge of interest within the computational linguistics (CL) community in the social dimension...
Expressive Power of Abstract Meaning Representations
Abstract grammatical meaning system translation logic current definition
2016/10/31
The syntax of abstract meaning representations (AMRs) can be defined recursively, and a systematic translation to first-order logic (FOL) can be specified, including a proper treatment of negation. AM...
String Kernels for Native Language Identification: Insights from Behind the Curtains
Text mining classification task depend on the characteristics of high level language features language task identity string
2016/10/31
The most common approach in text mining classification tasks is to rely on features like words, part-of-speech tags, stems, or some other high-level linguistic features. Recently, an approach that use...
All Mixed Up Finding the Optimal Feature Set for General Readability Prediction and Its Application to English and Dutch
Traditional readability forecast text type
2016/10/31
Readability research has a long and rich tradition, but there has been too little focus on general readability prediction without targeting a specific audience or text genre. Moreover, although NLP-in...
Parsing Linear Context-Free Rewriting Systems with Fast Matrix Multiplication
Subset of recognition algorithm the binary linear system M matrix multiplication grammar rules subroutine
2016/10/31
We describe a recognition algorithm for a subset of binary linear context-free rewriting systems (LCFRS) with running time O(nωd) where M(m) = O(mω) is the running time for m × m matrix multiplication...
Towards Accurate and Efficient Chinese Part-of-Speech Tagging
Structural linguistics aggregation vocabulary Chinese language processing data clustering syntax parsing
2016/10/31
From the perspective of structural linguistics, we explore paradigmatic and syntagmatic lexical relations for Chinese POS tagging, an important and challenging task for Chinese language processing. Pa...
Transition-Based Parsing for Deep Dependency Structures
Analysis of structure depth dependency structure language data drive
2016/10/31
Derivations under different grammar formalisms allow extraction of various dependency structures. Particularly, bilexical deep dependency structures beyond surface tree representation can be derived f...
Susan Armstrong worked as Professor of Translation Technology at the University of
Geneva until her retirement in 2014. She served as secretary to the European chapter of
the ACL from 1993–2000, rem...
When the Whole Is Less Than the Sum of Its Parts: How Composition Affects PMI Values in Distributional Semantic Vectors
Semantic Vectors PMI Values
2016/7/7
Distributional semantic models, deriving vector-based word representations from patterns of
word usage in corpora, have many useful applications (Turney and Pantel 2010). Recently, there
has been in...
Mining Parallel Corpora from Sina Weibo and Twitter
Mining Parallel Corpora Sina Weibo Twitter
2016/7/7
Microblogs such as Twitter, Facebook, and Sina Weibo (China’s equivalent of Twitter) are a
remarkable linguistic resource. In contrast to content from edited genres such as newswire,
microblogs cont...