搜索结果: 1-15 共查到“计算语言学 learning”相关记录48条 . 查询时间(0.083 秒)
Online Learning for Statistical Machine Translation
Online Learning Statistical Machine Translation
2016/4/7
We present online learning techniques for statistical machine translation (SMT). The availability of large training data sets that grow constantly over time is becoming more and more frequent in the f...
基于Active Learning的中文分词领域自适应
中文分词 领域自适应 主动学习
2016/2/24
在新闻领域标注语料上训练的中文分词系统在跨领域时性能会有明显下降。针对目标领域的大规模标注语料难以获取的问题,该文提出Active learning算法与n-gram统计特征相结合的领域自适应方法。该方法通过对目标领域文本与已有标注语料的差异进行统计分析,选择含有最多未标记过的语言现象的小规模语料优先进行人工标注,然后再结合大规模文本中的n-gram统计特征训练目标领域的分词系统。该文采用了CRF...
Cross-lingual Sentiment Lexicon Learning With Bilingual Word Graph Label Propagation
Sentiment Lexicon Learning Bilingual Word Graph Label
2015/9/15
In this article we address the task of cross-lingual sentiment lexicon learning, which aims to automatically generate sentiment lexicons for the target languages with available English sentiment lexic...
Entailment rules between predicates are fundamental to many semantic-inference applications. Consequently, learning such rules has been an active field of research in recent years. Methods for learnin...
Empirical Risk Minimization for Probabilistic Grammars:Sample Complexity and Hardness of Learning
Risk Minimization Probabilistic Grammars Sample Complexity and Hardness
2015/9/10
Probabilistic grammars are generative statistical models that are useful for compositional and sequential structures. They are used ubiquitously in computational linguistics. We present a framework, r...
This article presents our work on constructing a corpus of news articles in which events are annotated for estimated bounds on their duration, and automatically learning from this corpus. We describe ...
Learning Tractable Word Alignment Models with Complex Constraints
Learning Tractable Word Alignment Models Complex Constraints
2015/9/8
Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Probabilistic models for word alignment present a fundamental trade-off between richness of captured const...
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...
A Twin-Candidate Model for Learning-Based Anaphora Resolution
Computing language Twin-Candidate
2015/9/6
The traditional single-candidate learning model for anaphora resolution considers the antecedent
candidates of an anaphor in isolation, and thus cannot effectively capture the preference relationship...
Identifying Semitic Roots: Machine Learning with Linguistic Constraints
Linguistic Constraints Root
2015/9/6
Words in Semitic languages are formed by combining two morphemes: a root and a pattern. The
root consists of consonants only, by default three, and the pattern is a combination of vowels
and consona...
Classifying Non-Sentential Utterances in Dialogue: A Machine Learning Approach
Machine Learning Approach Dialogue
2015/9/2
In this article we use well-known machine learning methods to tackle a novel task, namely
the classification of non-sentential utterances (NSUs) in dialogue. We introduce a fine-grained
...
Subjectivity in natural language refers to aspects of language used to express opinions, evaluations, and speculations. There are numerous natural language processing applications for which subjectivi...
Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites
Document Warehouses Dedicated Web Sites
2015/8/31
We present a method and a tool, OntoLearn, aimed at the extraction of domain ontologies from
Web sites, and more generally from documents shared among the members of virtual organizations. OntoLearn ...
A Machine Learning Approach to Modeling Scope Preferences
Machine Learning Approac Modeling Scope Preferences
2015/8/28
This article describes a corpus-based investigation of quantifier scope preferences. Following recent work on multimodular grammar frameworks in theoretical linguistics and a long history of combining...
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 ...