Re:Google T5 scores 88.9 on SuperGLUE Benchmark, approaching...
by ekianjo on Friday October 25, 2019 @02:33AM
(#21352468)
A good demonstration that context (and cultural conditioning) is everything to understand what a text actually means.
[ Parent
| on HN ]
Re:Google T5 scores 88.9 on SuperGLUE Benchmark, approaching...
by otakucode on Friday October 25, 2019 @08:38AM
(#21354344)
Not to mention something that almost all NLP systems are resounding terrible at - short-term memory. If we've been talking about corporate financials for an hour and I say 'Justify the margins', it should be crystal clear what I mean. But most automated systems try to operate without a hint of memory or 'state' being tracked.