A lack of large-scale human-annotated data has hampered the hierarchical
discourse parsing of Chinese. In this paper, we present GCDT, the largest
hierarchical discourse treebank for Mandarin Chinese in the framework of
Rhetorical Structure Theory (RST). GCDT covers over 60K tokens across five
genres of freely available text, using the same relation inventory as
contemporary RST treebanks for English. We also report on this dataset's
parsing experiments, including state-of-the-art (SOTA) scores for Chinese RST
parsing and RST parsing on the English GUM dataset, using cross-lingual
training in Chinese and English with multilingual embeddings.

本文提出了 GCDT，这是目前最大的汉语层次化语篇树库，基于修辞结构理论，覆盖五种文本类型，使用与当代英语 RST 树库相同的关系清单。通过使用中英文多语言嵌入来训练语言关系，本文还介绍了这个数据集的分析实验，包括中英文 RST 解析和在英语 GUM 数据集上的 RST 解析，其中包括最先进（SOTA）的中文 RST 解析分数。

GCDT：一个适用于多类型和多语种篇章分析的汉语 RST 树库

GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing

Current state-of-the-art systems for sequence labeling are typically based on
the family of Recurrent Neural Networks (RNNs). However, the shallow
connections between consecutive hidden states of RNNs and insufficient modeling
of global information restrict the potential performance of those models. In
this paper, we try to address these issues, and thus propose a Global Context
enhanced Deep Transition architecture for sequence labeling named GCDT. We
deepen the state transition path at each position in a sentence, and further
assign every token with a global representation learned from the entire
sentence. Experiments on two standard sequence labeling tasks show that, given
only training data and the ubiquitous word embeddings (Glove), our GCDT
achieves 91.96 F1 on the CoNLL03 NER task and 95.43 F1 on the CoNLL2000
Chunking task, which outperforms the best reported results under the same
settings. Furthermore, by leveraging BERT as an additional resource, we
establish new state-of-the-art results with 93.47 F1 on NER and 97.30 F1 on
Chunking.

本文提出了一种名为 GCDT 的序列标签模型，它采用全局上下文增强和深层转换结构来解决循环神经网络在全局信息建模和浅层连接方面的不足，通过两项标准序列标签任务的实验结果，证明该方法在 NER 和 Chunking 任务上均能超越以往最佳结果，且利用 BERT 作为附加资源可进一步提升性能。