论文标题
用于标记，解析和诱饵的半监督神经系统
Semi-Supervised Neural System for Tagging, Parsing and Lematization
论文作者
论文摘要
本文介绍了ICS PAS系统，该系统参加了Conll 2018，共享有关从原始文本到通用依赖性的多语言解析的共享任务。该系统由训练有素的标记器，Lemmatizer和依赖解析器组成，这些解析器基于Bilstm网络提取的功能。该系统使用完全连接和扩张的卷积神经体系结构。我们方法的新颖性是使用额外的损耗函数，这减少了预测依赖图中的周期数，以及使用自训练来提高系统性能。拟议的系统，即ICS PAS（Warszawa），在官方评估中排名第3/4，获得以下总体结果：73.02（LAS），60.25（MLAS）和64.44（BLEX）（BLEX）。
This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. The system consists of jointly trained tagger, lemmatizer, and dependency parser which are based on features extracted by a biLSTM network. The system uses both fully connected and dilated convolutional neural architectures. The novelty of our approach is the use of an additional loss function, which reduces the number of cycles in the predicted dependency graphs, and the use of self-training to increase the system performance. The proposed system, i.e. ICS PAS (Warszawa), ranked 3th/4th in the official evaluation obtaining the following overall results: 73.02 (LAS), 60.25 (MLAS) and 64.44 (BLEX).
