Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning
نویسندگان
چکیده
منابع مشابه
Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning
Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the systems hard to scale. Recent years have witnessed a rise in statistical approaches to metaphor processing. However, these approaches often requir...
متن کاملUnsupervised and Semi-Supervised Multilingual Learning for Resource-Poor Languages
Název práce: Neř́ızené a poloř́ızené v́ıcejazyčné učeńı pro jazyky s nedostatkem zdroj̊u Autor: Manh-Ke Tran Katedra: Ústav formálńı a aplikované lingvistiky Vedoućı diplomové práce: RNDr. Daniel Zeman, Ph.D., Ústav formálńı a aplikované lingvistiky & Marco A. Wiering, Assistant professor, Artificial Intelligence department, University of Groningen Abstrakt: Práce se zaměřuje na neř́ızenou morfologi...
متن کاملEnsemble learning with trees and rules: Supervised, semi-supervised, unsupervised
In this article, we propose several new approaches for post processing a large ensemble of conjunctive rules for supervised, semi-supervised and unsupervised learning problems. We show with various examples that for high dimensional regression problems the models constructed by post processing the rules with partial least squares regression have significantly better prediction performance than ...
متن کاملContributions to Unsupervised and Semi-Supervised Learning
This thesis studies two problems in theoretical machine learning. The first part of the thesis investigates the statistical stability of clustering algorithms. In the second part, we study the relative advantage of having unlabeled data in classification problems. Clustering stability was proposed and used as a model selection method in clustering tasks. The main idea of the method is that from...
متن کاملSplitting the Unsupervised and Supervised Components of Semi-Supervised Learning
In this paper we investigate techniques for semi-supervised learning that split their unsupervised and supervised components — that is, an initial unsupervised phase is followed by a supervised learning phase. We first analyze the relative value of labeled and unlabeled data. We then present methods that perform “split” semi-supervised learning and show promising empirical results.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Linguistics
سال: 2017
ISSN: 0891-2017,1530-9312
DOI: 10.1162/coli_a_00275