Probabilistic CFG with Latent Annotations
Probabilistic CFG with Latent Annotations
复制标题
DOI：
10.3115/1219840.1219850
复制
发表时间：
2005-06
期刊：
影响因子：
--
通讯作者：
Takuya Matsuzaki;Yusuke Miyao;Junichi Tsujii
中科院分区：
文献类型：
--
作者：
Takuya Matsuzaki;Yusuke Miyao;Junichi Tsujii
本文定义了一个生成概率模型，我们称之为PCFG LA。该模型是PCFG的一个扩展，其中非终结符用潜变量进行了扩充。通过使用EM算法训练PCFG-LA模型，从解析的语料库中自动归纳细粒度的CFG规则。由于PCFG-LA的精确解析是NP难的，因此描述了几种近似并进行了经验比较。在使用Penn WSJ语料库的实验中，我们的自动训练模型给出了86.6%的性能（F1，句子≤ 40个单词），这与使用大量手动特征选择创建的未分类PCFG解析器的性能相当。
This paper defines a generative probabilistic model of parse trees, which we call PCFG-LA. This model is an extension of PCFG in which non-terminal symbols are augmented with latent variables. Fine-grained CFG rules are automatically induced from a parsed corpus by training a PCFG-LA model using an EM-algorithm. Because exact parsing with a PCFG-LA is NP-hard, several approximations are described and empirically compared. In experiments using the Penn WSJ corpus, our automatically trained model gave a performance of 86.6% (F1, sentences ≤ 40 words), which is comparable to that of an unlexicalized PCFG parser created using extensive manual feature selection.