Agreement/Disagreement Classification: Exploiting Unlabeled Data using Contrast Classifiers
نویسندگان
چکیده
Several semi-supervised learning methods have been proposed to leverage unlabeled data, but imbalanced class distributions in the data set can hurt the performance of most algorithms. In this paper, we adapt the new approach of contrast classifiers for semi-supervised learning. This enables us to exploit large amounts of unlabeled data with a skewed distribution. In experiments on a speech act (agreement/disagreement) classification problem, we achieve better results than other semi-supervised methods. We also obtain performance comparable to the best results reported so far on this task and outperform systems with equivalent feature sets.
منابع مشابه
Exploiting Unlabeled Data for Improving Accuracy of Predictive Data Mining
Predictive data mining typically relies on labeled data without exploiting a much larger amount of available unlabeled data. The goal of this paper is to show that using unlabeled data can be beneficial in a range of important prediction problems and therefore should be an integral part of the learning process. Given an unlabeled dataset representative of the underlying distribution and a K-cla...
متن کاملA Comparison of Discriminative EM-Based Semi-Supervised Learning algorithms on Agreement/Disagreement classification
Recently, semi-supervised learning has been an active research topic in the natural language processing community, to save effort in hand-labeling for data-driven learning and to exploit a large amount of readily available unlabeled text. In this paper, we apply EM-based semi-supervised learning algorithms such as traditional EM, co-EM, and cross validation EM to the task of agreement/disagreem...
متن کاملExploiting Unlabeled Data Using Improved Natural Langua
This paper presents an unsupervised method that uses limited amount of labeled data and a large pool of unlabeled data to improve natural language call routing performance. The method uses multiple classifiers to select a subset of the unlabeled data to augment limited labeled data. We evaluated four widely used text classification algorithms; Naive Bayes Classification (NBC), Support Vector ma...
متن کاملGeneralization Error Bounds Using Unlabeled Data
We present two new methods for obtaining generalization error bounds in a semi-supervised setting. Both methods are based on approximating the disagreement probability of pairs of classifiers using unlabeled data. The first method works in the realizable case. It suggests how the ERM principle can be refined using unlabeled data and has provable optimality guarantees when the number of unlabele...
متن کاملDetection Of Agreement vs. Disagreement In Meetings: Training With Unlabeled Data
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data set combined with supervised training on a small amount of data. For ASR transcripts with over 45% WER...
متن کامل