적절할 확률이 낮습니다. 이 단어를 시퀀스에 추가하고 다음 단어를 예측하면 올바른 확률이 낮
아질 가능성이 더 높아집니다. 따라서 예측된 단어가 거의 무작위한 것처럼 보이게 됩니다.
예를 들어 ‘
sweet
Jeremy
saw
Dublin
’에 있는 단어가 모두 말뭉치에 있지만 이 순서대로 있
지는 않습니다. 모델이 첫 번째 예측을 수행했을 때 단어 ‘
his
’가 가장 가능성 있는 후보로 선택
되었고
78
%의 꽤 높은 확률을 가졌습니다.
초기 텍스트: sweetJeremysawDublin
생성된 단어1: his
단계 1에서 상위 5개 예측:
his: 0.7782
go: 0.1393
bellows,: 0.0605
accident: 0.0090
til: 0.0048
이 단어를 시드 텍스트에 추가해 ‘
sweet
Jeremy
saw
Dublin
then
’을 만들면 훈련 데이터
에 없는 또 다른 구절이 됩니다. 이 문장에서 예측을 수행하면 가장 높은 확률인
44
%로 단어
‘
right
’이 선택됩니다.
생성된 단어2: right
단계 2에서 상위 5개 예측:predictionsforstep :
right: 0.7678
pipes,: 0.1376
creature: 0.0458
didnt: 0.0136
youll: 0.0113 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month, and much more.
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.