arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.01414cs.CLcs.LG
收藏

基于二阶推理和混合训练数据的增强通用依存句法分析

Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data

ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉成像工程研究中心);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Xinyu Wang, Yong Jiang, Kewei Tu

摘要:

本文介绍了我们提交给\textit{IWPT 2020 Shared Task}的系统。我们的系统是一个基于图的解析器与二阶推理。对于资源较少的泰米尔语语料,我们特别将泰米尔语的训练数据与其他语言混合,显著提高了泰米尔语的性能。由于我们对提交要求的误解,我们提交了没有连接的图表,这使得我们的系统只能将\textbf{6th}排在10个团队以上。然而,在我们解决了这个问题后,我们的系统比在官方结果中排名\textbf{1st}的团队高出0.6 ELAS。

英文摘要:

This paper presents the system used in our submission to the \textit{IWPT 2020 Shared Task}. Our system is a graph-based parser with second-order inference. For the low-resource Tamil corpus, we specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil. Due to our misunderstanding of the submission requirements, we submitted graphs that are not connected, which makes our system only rank \textbf{6th} over 10 teams. However, after we fixed this problem, our system is 0.6 ELAS higher than the team that ranked \textbf{1st} in the official results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑