Machine reading comprehension with Dr. T.J Hazen
1 172
11.5
Microsoft Research333 тыс
Следующее
22.08.19 – 6141:13:01Популярные
200 дней – 6293:07:51
Опубликовано 22 августа 2019, 16:28
Episode 86 | August 21, 2019
The ability to read and understand unstructured text, and then answer questions about it, is a common skill among literate humans. But for machines? Not so much. At least not yet! And not if Dr. T.J. Hazen, Senior Principal Research Manager in the Engineering and Applied Research group at MSR Montreal, has a say. He’s spent much of his career working on machine speech and language understanding, and particularly, of late, machine reading comprehension, or MRC.
On today’s podcast, Dr. Hazen talks about why reading comprehension is so hard for machines, gives us an inside look at the technical approaches applied researchers and their engineering colleagues are using to tackle the problem, and shares the story of how an a-ha moment with a Rubik’s Cube inspired a career in computer science and a quest to teach computers to answer complex, text-based questions in the real world.
See more at microsoft.com/en-us/research/b...
The ability to read and understand unstructured text, and then answer questions about it, is a common skill among literate humans. But for machines? Not so much. At least not yet! And not if Dr. T.J. Hazen, Senior Principal Research Manager in the Engineering and Applied Research group at MSR Montreal, has a say. He’s spent much of his career working on machine speech and language understanding, and particularly, of late, machine reading comprehension, or MRC.
On today’s podcast, Dr. Hazen talks about why reading comprehension is so hard for machines, gives us an inside look at the technical approaches applied researchers and their engineering colleagues are using to tackle the problem, and shares the story of how an a-ha moment with a Rubik’s Cube inspired a career in computer science and a quest to teach computers to answer complex, text-based questions in the real world.
See more at microsoft.com/en-us/research/b...
Свежие видео
7 дней – 4 0618:07
9 дней – 10 7552:29
9 дней – 1 337 18012:47
9 дней – 1 5100:10
11 дней – 7 8042:11Случайные видео
33 дня – 1 9800:30
307 дней – 2 6570:58
316 дней – 5280:35
30.01.22 – 1 3180:34
19.12.20 – 175 78318:11
19.09.08 – 84 5045:07
19 часов – 772:52
3 дня – 1 194 20716:12
4 дня – 1080:15
7 дней – 030:58
7 дней – 330 1904:22
8 дней – 5414:51
2 дня – 1 271 83520:29