arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1106.0220cs.AI
收藏

基于委员会的概率分类器样本选择

Committee-Based Sample Selection for Probabilistic Classifiers

Jerusalem College of Technology, Machon Lev(耶路撒冷理工学院(马洪莱夫));Bar-Ilan University(巴伊兰大学)

S. Argamon-Engelson, I. Dagan

摘要:

在许多现实世界的学习任务中,获取足够数量的标记样本进行训练是昂贵的。本文研究了通过“样本选择”来降低标注成本的方法。在这种方法中,在训练过程中,学习程序会检查许多未标记的示例,并只选择在每个阶段信息量最大的示例进行标记。这就避免了对那些几乎没有新信息的例子进行冗余标记。我们的工作遵循以前的研究查询委员会,扩展基于委员会的范例的概率分类的上下文中。我们描述了一个家庭的经验方法,以委员会为基础的样本选择概率分类模型,通过测量几个模型变量之间的分歧程度来评估一个例子的信息量。这些变量(委员会)是从迄今为止标记的训练集条件下的概率分布中随机抽取的。该方法被应用到现实世界的随机词性标注的自然语言处理任务。我们发现,该方法的所有变体都实现了注释成本的显着降低,尽管它们的计算效率不同。特别是,最简单的变体,一个两个成员的委员会,没有参数调整,给出了很好的结果。我们还表明,样本的选择产生了显着减少所使用的标签的模型的大小。

英文摘要:

In many real-world learning tasks, it is expensive to acquire a sufficient number of labeled examples for training. This paper investigates methods for reducing annotation cost by `sample selection'. In this approach, during training the learning program examines many unlabeled examples and selects for labeling only those that are most informative at each stage. This avoids redundantly labeling examples that contribute little new information. Our work follows on previous research on Query By Committee, extending the committee-based paradigm to the context of probabilistic classification. We describe a family of empirical methods for committee-based sample selection in probabilistic classification models, which evaluate the informativeness of an example by measuring the degree of disagreement between several model variants. These variants (the committee) are drawn randomly from a probability distribution conditioned by the training set labeled so far. The method was applied to the real-world natural language processing task of stochastic part-of-speech tagging. We find that all variants of the method achieve a significant reduction in annotation cost, although their computational efficiency differs. In particular, the simplest variant, a two member committee with no parameters to tune, gives excellent results. We also show that sample selection yields a significant reduction in the size of the model used by the tagger.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑