【摘 要】
：
Most researches to SRL focus on English.It is still a challenge to improve the SRL performance of other language.In this paper,we introduce a two-pass appro
【机 构】
：
Key Laboratory of Computational Linguistics,Ministry of Education,School of Electronics Engineering
【出 处】
：
第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD
论文部分内容阅读
Most researches to SRL focus on English.It is still a challenge to improve the SRL performance of other language.In this paper,we introduce a two-pass approach to do Chinese SRL with a Recurrent Neural Network(RNN)model.We use English Proposition Bank(EPB)to improve the performance of Chinese SRL.Experimental result shows a significant improvement over the state-of-the-art methods on Chinese Proposition Bank(CPB),which reaches 78.39%F1 score.
其他文献
The dialog manager is the most important component for a dialog system,in which the dialog state tracking is crucial to a real-world system.We claim that th
The algorithms for discovering global community structure require the knowledge about entire network structures,which are still difficult and unrealistic to
Finding similarity degree is one of the significant technologies used in the sample-based machine translation.It works in the following principle,first matc
Previous work has shown that joint modeling of two Natural Language Processing(NLP)tasks are effective for achieving better performances for both tasks.Lots
The rapid development of new media results in a lot of redundant information,increasing the difficulty of quickly obtaining useful information and browsing
This paper describes a mixing model of joint POS tagging and chunking for Kazakh where partial optimal solution provide feature information for joint model.
In this paper,we propose a neural graph-based dependency parsing model which utilizes hierarchical LSTM networks on character level and word level to learn
Traditional Mongolian Unicode Encoding has serious problems as several pairs of vowels with the same glyphs but different pronunciations are coded different
This paper describes an approach to identify suspected cybermob on social media.Many researches involve making predictions of group emotion on Internet(such
在利用大规模双语语料获取复述知识方面,传统的基于"枢轴"方法只能考虑两步以内的复述现象.本文针对已有方法的局限性,对不同语言之间互为翻译的短语对构建翻译关系图,提出基于随机行走N步的复述获取算法,改进已有方法以获取更多潜在的复述知识.本文描述了由汉英短语翻译表构建翻译关系图的方法、基于N步的随机行走算法和基于期望步数的复述短语可信度计算方法.同时,本文提出面向多语言对的翻译关系图扩展方法.在NTC