硕士生导师
个人信息Personal Information
学历:博士研究生毕业
学位:工学博士学位
办公地点:犀浦3号教学楼31529
毕业院校:四川大学
学科:电子信息. 软件工程. 计算机应用技术
所在单位:计算机与人工智能学院
报考该导师研究生的方式
欢迎你报考王红军老师的研究生,报考有以下方式:
1、参加西南交通大学暑期夏令营活动,提交导师意向时,选择王红军老师,你的所有申请信息将发送给王红军老师,老师看到后将和你取得联系,点击此处参加夏令营活动
2、如果你能获得所在学校的推免生资格,欢迎通过推免方式申请王红军老师研究生,可以通过系统的推免生预报名系统提交申请,并选择意向导师为王红军老师,老师看到信息后将和你取得联系,点击此处推免生预报名
3、参加全国硕士研究生统一招生考试报考王红军老师招收的专业和方向,进入复试后提交导师意向时选择王红军老师。
4、如果你有兴趣攻读王红军老师博士研究生,可以通过申请考核或者统一招考等方式报考该导师博士研究生。
The Errors Analysis of Natural Language Generation - A Case Study of Topic-to-Essay Generation
DOI码:10.1109/CIS52066.2020.00027
所属单位:西南交通大学
发表刊物:2020 16th International Conference on Computational Intelligence and Security (CIS)
刊物所在地:Guangxi, China
关键字:Annotations,Error analysis,Natural languages,Neural networks,Coherence,Manuals
摘要:Although natural language generation (NLG) has achieved great success, there are still many problems with the generated text, if humans carefully examine it. To analyze the problems of NLG, we use manual evaluation methods to annotate and analyze the text generated by NLG. According to the analysis results, we can understand the defects of NLG in-depth, comprehensively, and accurately. Further, these provide cues for future improvement. In this paper, we first use a state-of-the-art Topic-to-Essay generation model to generate texts conditional on some topic words. Then, by analyzing the generated text, we propose an annotation framework, and then quantify the main drawbacks of current NLG, including poor semantic coherence, content duplication, logic errors, and repetition. It shows that the text generated by the current sequence-to-sequence model is still far from human expectation.
合写作者:Xingyuan Chen,Peng Jin
第一作者:Cai Ping
论文类型:学术论文
通讯作者:Hongjun Wang
论文编号:20211910316120
学科门类:工学
一级学科:计算机科学与技术
是否译文:否
发表时间:2021-05-27