中国科学院自动化研究所   设为首页   加入收藏  联系我们
 
English
网站首页     实验室概况     研究队伍     组织机构     学术交流     科研成果     人才培养     开放课题     创新文化     资源共享     联系我们
    学术讲座

Setting Appropriate Expectations: Are Deep Nets Too Hot? Too Cold? Or Just Right?

模式识别学术大讲堂
Advanced Lecture Series in Pattern Recognition

题     目 (TITLE):Setting Appropriate Expectations: Are Deep Nets Too Hot? Too Cold? Or Just Right?

讲 座 人 (SPEAKER):Prof. Kenneth Church

主 持 人 (CHAIR):Prof. Chengqing Zong

时     间 (TIME): 15:00, Jan. 13 (Monday), 2020

地     点 (VENUE):No.1 Conference Room (3rd floor), Intelligence Building

报告摘要(ABSTRACT):

There is considerable excitement over deep nets, and for good reasons. More and more people are attending more and more conferences on Machine Learning. Deep nets have produced substantial progress on a number of benchmarks, especially in vision and speech. This progress is changing the world in all kinds of ways. Face recognition and speech recognition are everywhere.  When friends and family used to ask me about my work, I used to have to explain what AI and speech recognition were, but that's no longer necessary now that everyone has experience with such technologies.  Most people know that AI works well in simple cases (monologues with clean speech), but dialogues are proving more challenging than monologues, and the cocktail party effect is likely to remain well beyond the state of the art for some time to come. We created the DIHARD challenge (https://coml.lscp.ens.fr/dihard/index.html) to encourage the community to work on diarization (who spoke when), a problem that many thought was solved, based on some early successes.  We were so pleased to see that the community found DIHARD 2018 to be both hard and worthwhile that we did it again (see DIHARD 2019).   More generally,  we have had some successes, and that is a wonderful thing, but much work remains to be done.  As Feynman said, "you must not fool yourself -- and you are the easiest person to fool."  

报告人简介(BIOGRAPHY):

Kenneth Church has worked on many topics in computational linguistics including: web search, language modeling, text analysis, spelling correction, word-sense disambiguation, terminology, translation, lexicography, compression, speech (recognition, synthesis & diarization), OCR, as well as applications that go well beyond computational linguistics such as revenue assurance and virtual integration (using screen scraping and web crawling to integrate systems that traditionally don't talk together as well as they could such as billing and customer care). He enjoys working with large corpora such as the Associated Press newswire (1 million words per week) and even larger datasets such as telephone call detail (1-10 billion records per month) and web logs. He earned his undergraduate and graduate degrees from MIT, and has worked at AT&T, Microsoft, Hopkins, IBM and Baidu. He was the president of ACL in 2012, and SIGDAT (the group that organizes EMNLP) from 1993 until 2011. He became an AT&T Fellow in 2001 and ACL Fellow in 2015.


友情链接
 
中科院自动化研究所 模式识别国家重点实验室 事业单位  京ICP备14019135号-3
NLPR, INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES