BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Computer Science - ECPv5.12.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Computer Science
X-ORIGINAL-URL:https://www.cs.jhu.edu
X-WR-CALDESC:Events for Department of Computer Science
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20191112T104500
DTEND;TZID=America/New_York:20191112T114500
DTSTAMP:20220112T093559
CREATED:20210629T210720Z
LAST-MODIFIED:20210629T210720Z
UID:1962365-1573555500-1573559100@www.cs.jhu.edu
SUMMARY:CS Seminar: Matt Post – “Putting the “human” in human-parity machine translation”
DESCRIPTION:LocationHackerman Hall B-17AbstractIf you’re a layperson who gets your news from public relations firmsat major industry research centers\, you may think that machinetranslation is solved\, having reached “human parity” sometime in thepast few years. But the reality is quite different. While translationaccuracy is indistinguishable from that of humans by somedefinitions in certain narrow settings\, claims of human parity rest onan impoverished definition of human capability. This talk will explorethree lines of work whose collective goal is to provide neural machinetranslation systems with a few abilities that come quite naturally tous but are less natural in the modern translation paradigm\, namely:translating under supplied constraints\, producing diverse translationcandidates\, and evaluating output more robustly.BioMatt Post is a research scientist at the Human Language TechnologyCenter of Excellence at JHU\, with appointments the Department ofComputer Science and at the Center for Language and Speech Processing.He spends most of his time doing machine translation\, but he has alsoworked on text classification\, grammatical error correction\, and humanevaluation\, and is interested in most topics in natural languageprocessing. He is the Director of the ACL Anthology\, and for manyyears has helped to organize the annual Conference on MachineTranslation (WMT). He spent the 2017–2018 academic year working withAmazon Research in Berlin.VideoWatch seminar video.
URL:https://www.cs.jhu.edu/event/cs-seminar-matt-post-putting-the-human-in-human-parity-machine-translation/
END:VEVENT
END:VCALENDAR