This paper introduces a semi-supervised learning framework for creating training material, namely active annotation. The main intuition is that an unsupervised method is used to initially annotate imperfectly the data and then the errors made are detected automatically and corrected by a human annotator. We applied active annotation to named entity recognition in the biomedical domain and encou...

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we int...

We present a new active learning approach to incorporate human feedback for on-line unusual event detection. In contrast to most existing unsupervised methods that perform passive mining for unusual events, our approach automatically requests supervision for critical points to resolve ambiguities of interest, leading to more robust and accurate detection on subtle unusual events. The active lea...

Semi-supervised clustering uses a small amount of supervised data to aid unsupervised learning. One typical approach specifies a limited number of must-link and cannotlink constraints between pairs of examples. This paper presents a pairwise constrained clustering framework and a new method for actively selecting informative pairwise constraints to get improved clustering performance. The clust...

In this paper, we introduce a new type of information-theoretic method called “information-theoretic active SOM”, based on the self-organizing maps (SOM) for training multi-layered neural networks. The SOM is one of the most important techniques in unsupervised learning. However, SOM knowledge is sometimes ambiguous and cannot be easily interpreted. Thus, we introduce the information-theoretic ...

This paper presents an adaptive learning framework for Phonetic Similarity Modeling (PSM) that supports the automatic construction of transliteration lexicons. The learning algorithm starts with minimum prior knowledge about machine transliteration, and acquires knowledge iteratively from the Web. We study the active learning and the unsupervised learning strategies that minimize human supervis...

There are mainly two kinds of methods for document-level sentiment classification, unsupervised learning and supervised learning. When ensemble learning is introduced, existing methods only combine unsupervised learning algorithms or supervised learning algorithms. To overcome each other’s flaws, a novel sentiment classification method based on behavior-knowledge space is proposed, in which two...

This paper presents our approach to the PAN 2012 Traditional Authorship Attribution tasks and the Sexual Predator Identification task. We approached these tasks with machine learning methods that work at the character level. More precisely, we treated texts as just sequences of symbols (strings) and used string kernels in conjunction with different kernel-based learning methods: supervised and ...

We introduce a method for error detection in automatically annotated text, aimed at supporting the creation of high-quality language resources at affordable cost. Our method combines an unsupervised generative model with human supervision from active learning. We test our approach on in-domain and out-of-domain data in two languages, in AL simulations and in a real world setting. For all settin...