Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model
Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model
复制标题
DOI：
--
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Ivan Titov;James Henderson
中科院分区：
文献类型：
--
作者：
Ivan Titov;James Henderson
我们使用一个基于生成历史的模型来预测最有可能的依赖解析的推导。我们的概率模型是基于增量Sigmoid信念网络，最近提出的一类结构预测的潜变量模型。它们自动归纳特征的能力导致了多语言解析，这种解析足够强大，可以在CoNLL-2007共享任务的多语言轨道中实现远高于每种语言平均水平的准确性。这种鲁棒性导致了第三个最好的整体平均标记的附件得分的任务，尽管没有使用歧视性的方法。我们还证明了解析器是相当快的，可以提供更快的解析时间，而不会损失太多的准确性。
We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a recently proposed class of latent variable models for structure prediction. Their ability to automatically induce features results in multilingual parsing which is robust enough to achieve accuracy well above the average for each individual language in the multilingual track of the CoNLL-2007 shared task. This robustness led to the third best overall average labeled attachment score in the task, despite using no discriminative methods. We also demonstrate that the parser is quite fast, and can provide even faster parsing times without much loss of accuracy.