Open AccessProceedings Article
Cross-Language Text Classification Using Structural Correspondence Learning
Peter Prettenhofer,Benno Stein +1 more
- pp 1118-1127
TLDR
A new approach to cross-language text classification that builds on structural correspondence learning, a recently proposed theory for domain adaptation, is presented, using unlabeled documents, along with a simple word translation oracle, in order to induce task-specific, cross-lingual word correspondences.Abstract:
We present a new approach to cross-language text classification that builds on structural correspondence learning, a recently proposed theory for domain adaptation. The approach uses unlabeled documents, along with a simple word translation oracle, in order to induce task-specific, cross-lingual word correspondences. We report on analyses that reveal quantitative insights about the use of unlabeled data and the complexity of inter-language correspondence modeling.
We conduct experiments in the field of cross-language sentiment classification, employing English as source language, and German, French, and Japanese as target languages. The results are convincing; they demonstrate both the robustness and the competitiveness of the presented ideas.read more
Citations
More filters
Journal ArticleDOI
Cross-lingual learning for text processing: A survey
TL;DR: The most important contribution of this work is that it identifies and analyze four types of cross-lingual transfer based on “what” is being transferred, which might help other NLP researchers and practitioners to understand how to use cross-lingsual learning for wide range of problems.
Journal ArticleDOI
A Systematic Review on Data Scarcity Problem in Deep Learning: Solution and Applications
TL;DR: The purpose of this study focuses on various data augmentation techniques that can be used to further improve the accuracy of a neural network by augmenting available data.
Proceedings ArticleDOI
Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages
TL;DR: This work proposes a meta graph learning (MGL) method, which can learn to cross-lingual transfer by extracting meta-knowledge from historical CLT experiences (tasks), making mPLM insensitive to low-resource languages.
Proceedings Article
A Multilingual, Multi-Style and Multi-Granularity Dataset for Cross-Language Textual Similarity Detection
TL;DR: The proposed dataset is multilingual, includes cross-language alignment for different granularities (from chunk to document), is based on both parallel and comparable corpora and contains human and machine translated texts.
Proceedings Article
Cross-lingual dataless classification for many languages
TL;DR: This paper uses CLESA (cross-lingual explicit semantic analysis) to embed both foreign language documents and an English label space into a shared semantic space, and select the best label(s) for a document using the similarity between the corresponding semantic representations.
References
More filters
Journal ArticleDOI
Regularization and variable selection via the elastic net
Hui Zou,Trevor Hastie +1 more
TL;DR: It is shown that the elastic net often outperforms the lasso, while enjoying a similar sparsity of representation, and an algorithm called LARS‐EN is proposed for computing elastic net regularization paths efficiently, much like algorithm LARS does for the lamba.
Thumbs up? Sentiment Classiflcation using Machine Learning Techniques
TL;DR: In this paper, the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, was considered and three machine learning methods (Naive Bayes, maximum entropy classiflcation, and support vector machines) were employed.
Proceedings ArticleDOI
Thumbs up? Sentiment Classification using Machine Learning Techniques
TL;DR: This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
Proceedings Article
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
TL;DR: This work extends to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline.
Journal ArticleDOI
Pegasos: primal estimated sub-gradient solver for SVM
TL;DR: A simple and effective stochastic sub-gradient descent algorithm for solving the optimization problem cast by Support Vector Machines, which is particularly well suited for large text classification problems, and demonstrates an order-of-magnitude speedup over previous SVM learning methods.