隐马尔可夫链、熵前向-后向和词性标注
Hidden Markov Chains, Entropic Forward-Backward, and Part-Of-Speech Tagging
摘要：
在自然语言处理（NLP）问题中，考虑观察的特征（也称为特征）的能力是必不可少的。隐马尔可夫链（HMC）模型与经典的前向-后向概率相关联，不能处理任意大小的前缀或后缀等任意特征，除非具有独立性条件。20年来，这一预设鼓励了其他序列模型的发展，从最大熵马尔可夫模型（MEMM）开始，它优雅地整合了任意特征。更普遍的是，它导致了对NLP的HMC的忽视。在本文中，我们表明，这个问题是不是由于HMC本身，但其恢复算法的计算方式。我们提出了一种新的方法来计算HMC的基础上的简化使用原来的熵向前和熵向后（EFB）的概率。我们的方法允许考虑HMC框架中的功能，以相同的方式在MEMM框架。我们说明了HMC使用EFB在词性标注中的效率，显示了其优于基于MEMM的恢复。作为一个角度，我们还指定了带有EFB的HMC如何作为递归神经网络的替代方案，以深度架构处理序列数据。
英文摘要：
The ability to take into account the characteristics - also called features - of observations is essential in Natural Language Processing (NLP) problems. Hidden Markov Chain (HMC) model associated with classic Forward-Backward probabilities cannot handle arbitrary features like prefixes or suffixes of any size, except with an independence condition. For twenty years, this default has encouraged the development of other sequential models, starting with the Maximum Entropy Markov Model (MEMM), which elegantly integrates arbitrary features. More generally, it led to neglect HMC for NLP. In this paper, we show that the problem is not due to HMC itself, but to the way its restoration algorithms are computed. We present a new way of computing HMC based restorations using original Entropic Forward and Entropic Backward (EFB) probabilities. Our method allows taking into account features in the HMC framework in the same way as in the MEMM framework. We illustrate the efficiency of HMC using EFB in Part-Of-Speech Tagging, showing its superiority over MEMM based restoration. We also specify, as a perspective, how HMCs with EFB might appear as an alternative to Recurrent Neural Networks to treat sequential data with a deep architecture.
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。
