讲座时间：2022年6月21日 下午15:00–16:00

讲座地点： 腾讯会议：947 570 726

主讲人：香港中文大学（深圳）贺品嘉 助理教授、副研究员

讲座题目：Toward Reliable NLP Systems via Software Testing

摘要:

NLP systems such as machine translation have been increasingly utilized in our daily lives. Thus, their reliability becomes critical; mistranslations by Google Translate, for example, can lead to misunderstanding, financial loss, threats to personal safety and health, etc. On the other hand, due to their complexity, such systems are difficult to get right.  Because of their nature (i.e., based on large, complex neural networks), traditional reliability techniques are challenging to be applied. In this talk, I will present my recent work that has spearheaded the testing of machine translation systems, toward building reliable NLP systems. In particular, I will describe three complementary approaches which collectively found 1,000+ diverse translation errors in the widely-used Google Translate and Bing Microsoft Translator.

主讲人简历:

贺品嘉 香港中文大学（深圳）助理教授，副研究员，校长青年学者，博士生导师。博士毕业于香港中文大学，在苏黎世联邦理工学院任职博士后三年。研究方向为软件可靠性、软件测试、MLOps、智能运维等。近年来在ICSE, FSE, ASE, ISSTA, OSDI, CSUR, TDSC等顶级会议期刊发表学术论文20余篇。获得ISSRE最有影响力论文奖。Google Scholar引用超2300次，H-Index为19。主导的自动化日志分析开源项目LogPAI在GitHub上被star 3000余次，并被380多个学界业界组织下载7万余次。