搜索结果: 1-15 共查到“知识库 应用语言学 data”相关记录25条 . 查询时间(0.261 秒)
Data-Driven Parsing using Probabilistic Linear Context-Free Rewriting Systems
Context-Free Rewriting Systemsl Data-Driven Parsing
2015/9/11
This paper presents the first efficient implementation of a weighted deductive CYK parser for
Probabilistic Linear Context-Free Rewriting Systems (PLCFRSs). LCFRS, an extension of CFG,
c...
Learning and Evaluation of Dialogue Strategies for New Applications: Empirical Methods for Optimization from Small Data Sets
New Applications Small Data Sets
2015/9/9
We present a new data-driven methodology for simulation-based dialogue strategy learning,
which allows us to address several problems in the field of automatic optimization of dialogue
strateg...
Generating Phrasal and Sentential Paraphrases:A Survey of Data-Driven Methods
Generating Phrasal Sentential Paraphrases Data-Driven Methods
2015/9/8
The task of paraphrasing is inherently familiar to speakers of all languages. Moreover, the task of automatically generating or extracting semantic equivalences for the various units of language—words...
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
data set Computing language
2015/9/6
We propose a method for learning dialogue management policies from a fixed data set. The method
addresses the challenges posed by Information State Update (ISU)-based dialogue systems, which
r...
Coherence in Natural Language:Data Stuctures and Applications
Natural Language Data Stuctures and Applications
2015/9/2
In his blurb on the back cover, Mark Liberman calls this book “the biggest step forward [in research on discourse structure] since Aristotle.” Given this eminent recommendation, I read the book with g...
Never say “never.” In 1997, most experts would have sworn that text-to-speech (TTS)
synthesis technologies had reached a plateau, from which it would be very hard to
leave. Five years later, speech ...
Understanding Failures of Learning:Hebbian Learning,Competition for Representational Space,and some Preliminary Experimental Data
Understanding Failures of Learning Hebbian Learning Competition for Representational Space Experimental Data
2015/6/19
The availability of powerful learning algorithms such as back-propagation has created a situation in which we now know how to teach neural networks many complex things. Models that use back propagatio...
Crowdsourcing and language studies: the new generation of linguistic data
Crowdsourcing language linguistic data
2015/6/15
We present a compendium of recent and current projects that utilize crowdsourcing technologies for language studies, finding that the quality is comparable to controlled laboratory experiments, and in...
LAF-Fabric: a data analysis tool for Linguistic Annotation Framework with an application to the Hebrew Bible
LAF-Fabric data analysis tool Linguistic Annotation Framework the Hebrew Bible
2015/5/6
The Linguistic Annotation Framework (LAF) provides a general, extensible stand-off markup system for corpora. This paper discusses LAF-Fabric, a new tool to analyse LAF resources in general with an ex...
Detection of Runs of Homozygosity from Whole Exome Sequencing Data: State of the Art and Perspectives for Clinical, Population and Epidemiological Studies
Exome sequencing Runs of homozygosity Homozygosity mapping
2015/5/5
Runs of homozygosity (ROH) are sizeable stretches of homozygous genotypes at consecutive polymorphic DNA marker positions, traditionally captured by means of genome-wide single nucleotide polymorphism...
H3M2:detection of runs of homozygosity from whole-exome sequencing data
H3M2 runs of homozygosity whole-exome sequencing data
2015/5/5
Motivation: Runs of homozygosity (ROH) are sizable chromosomal stretches of homozygous genotypes, ranging in length from tens of kilobases to megabases. ROHs can be relevant for population and medical...
A data infrastructure reference model with applications: towards realization of a ScienceTube vision with a data replication service
Reference model ScienceTube Data infrastructure Replication
2015/4/24
The wide variety of scientific user communities work with data since many years and thus have already a wide variety of data infrastructures in production today. The aim of this paper is thus not to c...
ISOcat Data Categories for Signed Language Resources
signed language resources metadata data categories standardization
2015/4/21
As the creation of signed language resources is gaining speed worldwide, the need for standards in this field becomes more acute. This paper discusses the state of the field of signed language resourc...
LAT Bridge: Bridging tools for annotation and exploration of rich linguistic data
LAT Bridge Bridging tools for annotation rich linguistic data
2015/4/9
We present a software module, the LAT Bridge, which enables bidirectional communication between the annotation and exploration tools developed at the Max Planck Institute for Psycholinguistics as part...
A Data Category Registry- and Component-based Metadata Framework
A Data Category Registry Metadata Framework
2015/4/8
We describe our computer-supported framework to overcome the rule of metadata schism. It combines the use of controlled vocabularies,managed by a data category registry, with a component-based approac...