We describe two end-to-end autoencoding models for semi-supervised
graph-based projective dependency parsing. The first model is a Locally
Autoencoding Parser (LAP) encoding the input using continuous latent variables
in a sequential manner; The second model is a Globally Autoencoding Parser
(GAP) encoding the input into dependency trees as latent variables, with exact
inference. Both models consist of two parts: an encoder enhanced by deep neural
networks (DNN) that can utilize the contextual information to encode the input
into latent variables, and a decoder which is a generative model able to
reconstruct the input. Both LAP and GAP admit a unified structure with
different loss functions for labeled and unlabeled data with shared parameters.
We conducted experiments on WSJ and UD dependency parsing data sets, showing
that our models can exploit the unlabeled data to improve the performance given
a limited amount of labeled data, and outperform a previously proposed
semi-supervised model.

通过深度神经网络处理输入进一步编码为潜在变量，包括在序列中使用连续潜在变量对输入进行编码的局部自编码分析器（LAP）和在依存树中使用依赖树作为潜在变量对输入进行编码的全局自编码分析器（GAP），使用统一结构和不同的损失函数处理有标记和无标记的数据，并在 WSJ 和 UD 依存解析数据集上进行实验，展示模型能够利用未标记的数据来提高性能，并超越以前提出的半监督模型。