This paper describes a parsing model that combines the exact dynamic
programming of CRF parsing with the rich nonlinear featurization of neural net
approaches. Our model is structurally a CRF that factors over anchored rule
productions, but instead of linear potential functions based on sparse
features, we use nonlinear potentials computed via a feedforward neural
network. Because potentials are still local to anchored rules, structured
inference (CKY) is unchanged from the sparse case. Computing gradients during
learning involves backpropagating an error signal formed from standard CRF
sufficient statistics (expected rule counts). Using only dense features, our
neural CRF already exceeds a strong baseline CRF model (Hall et al., 2014). In
combination with sparse features, our system achieves 91.1 F1 on section 23 of
the Penn Treebank, and more generally outperforms the best prior single parser
results on a range of languages.

本文利用神经网络方法，结合了准确的 CRF 解析动态规划和丰富的非线性特征，提出了一种解析模型。该模型结构上基于 CRF，以锚定规则制作因素，而不是使用基于稀疏特征的线性势函数，使用前馈神经网络计算非线性势函数。在 Penn Treebank 第 23 节上，我们的系统优于先前最佳单个解析器结果，F1 分数达到 91.1。