搜索结果: 1-15 共查到“普通语言学 Learning”相关记录123条 . 查询时间(0.14 秒)
Learning Dependency-Based Compositional Semantics
Semantics Relationship
font style='font-size:12px;'>
2015/9/11
Suppose we want to build a system that answers a natural language question by representing its
semantics as a logical form and computing the answer given a structured database of facts. The
core par...
Learning Entailment Relations by Global Graph Structure Optimization
Structure Optimization Entailment Relations
font style='font-size:12px;'>
2015/9/10
Identifying entailment relations between predicates is an important part of applied semantic
inference. In this article we propose a global inference algorithm that learns such entailment
rules. Fir...
Unsupervised Learning of Morphology
word language
font style='font-size:12px;'>
2015/9/9
This article surveys work on Unsupervised Learning of Morphology. We define Unsupervised
Learning of Morphology as the problem of inducing a description (of some kind, even if only
morpheme se...
How Nature Meets Nurture:Universal Grammar and Statistical Learning
language acquisition syntax statistical inference input intake
font style='font-size:12px;'>
2015/9/2
Evidence of children’s sensitivity to statistical features of their input in
language acquisition is often used to argue against learning mechanisms
driven by innate knowledge. At the same time, evi...
When Domain-General Learning Fails and When It Succeeds: Identifying the Contribution of Domain Specificity
Domain Specificity Learning Fails
font style='font-size:12px;'>
2015/9/2
We identify three components of any learning theory: the representations, the learner’s data intake,
and the learning algorithm. With these in mind, we model the acquisition of the English anaphoric
...
SELECTIVE LEARNING IN THE ACQUISITION OF KANNADA DITRANSITIVES
quantification binding acquisition syntax
font style='font-size:12px;'>
2015/9/2
In this article we offer up a particular linguistic phenomenon, quantifier-variable binding in
Kannada ditransitives, as a proving ground upon which competing claims about learnability can
be evalua...
Similar neural correlates for language and sequential learning: Evidence from event-related brain potentials
Event-related potentials (ERPs) Sequential learning
font style='font-size:12px;'>
2015/8/10
We used event-related potentials (ERPs) to investigate the time course and distribution of
brain activity while adults performed (1) a sequential learning task involving complex
structured sequences...
Processing multiple non-adjacent dependencies: evidence from sequence learning
non-adjacent dependencies sequence learning
font style='font-size:12px;'>
2015/8/10
Processing non-adjacent dependencies is considered to be one of the hallmarks of human language.
Assuming that sequence-learning tasks provide a useful way to tap natural-language-processing
mechani...
Learning Algorithms for Keyphrase Extraction
achine learning summarization indexing keywords keyphrase extraction
font style='font-size:12px;'>
2015/7/30
Many academic journals ask their authors to provide a list of about five to fifteen keywords,
to appear on the first page of each article. Since these key words are often phrases of two or
more word...
Corpus-based Learning of Analogies and Semantic Relations
analogy metaphor semantic relations Vector Space Model cosine similarity noun-modifier pairs
font style='font-size:12px;'>
2015/7/30
We present an algorithm for learning from unlabeled text, based on the Vector Space Model (VSM) of information retrieval, that can solve verbal analogy questions of the kind found in the SAT college e...
Compositionality:The Formation of a Learning Theory
Compositionality:Learning Theory
font style='font-size:12px;'>
2015/7/30
A learning theory should try to answer the following questions. What does it mean to learn? How is something learnt? How is the learnt information stored, processed and ultimately translated into the ...
Using Speakers’ Referential Intentions to Model Early Cross-Situational Word Learning
word meaning
font style='font-size:12px;'>
2015/6/24
Word learning is a ‘‘chicken and egg’’ problem. If a child could understand speakers’ utterances, it
would be easy to learn the meanings of individual words,
and once a child knows what many words m...
Learning hierarchical category structure in deep neural networks
neural networks hierarchical generative models semantic cognition learning dynamics
font style='font-size:12px;'>
2015/6/23
Psychological experiments have revealed remarkable regularities in the developmental time course of cognition. Infants generally acquire broad categorical distinctions (i.e., plant/animal) before fine...
Learning to discriminate English /r/ and /l/ in adulthood: Behavioral and modeling studies
discriminate English /r/ /l/ Behavioral modeling
font style='font-size:12px;'>
2015/6/23
I describe a body of work undertaken to explore the effect of experience on the perception of speech sounds. The work is undertaken within the context of my overall theoretical perspective, in which l...
Connectionist perspectives on language learning,representation and processing
Connectionist perspectives language learning representation processing
font style='font-size:12px;'>
2015/6/23
The field of formal linguistics was founded on the premise that language is mentally represented as a deterministic symbolic grammar. While this approach has captured many important characteristics of...