Adversarial Training for Cross-Domain Universal Dependency Parsing
Adversarial Training for Cross-Domain Universal Dependency Parsing
复制标题
DOI：
10.18653/v1/k17-3007
复制
发表时间：
2017
影响因子：
8.6
通讯作者：
Motoki Sato;Hitoshi Manabe;Hiroshi Noji;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Motoki Sato;Hitoshi Manabe;Hiroshi Noji;Yuji Matsumoto
我们描述了我们对CoNLL 2017共享任务的提交，该任务通过域适应技术利用不同领域的语言共享常识。我们的方法是对最近提出的用于域适应的对抗训练技术的扩展，我们将其应用于双向LSTM上基于图的神经依赖解析模型。在我们的实验中，我们发现我们的基线基于图的解析器已经远远优于官方基线模型（UDPipe）。此外，通过将我们的技术应用于具有不同领域的相同语言的树库，我们观察到性能的额外增益，特别是对于训练数据较少的领域。
We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on bidirectional LSTMs. In our experiments, we find our baseline graph-based parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same language with different domains, we observe an additional gain in the performance, in particular for the domains with less training data.