摘要:
第一次使用BERT时,发现如果我的输入是[1,512]的形状的 (512个token的index),那么输入就会是[1,512,768],这个时候就麻了,为啥会有512个768呀,虽然说我有512个输入,但是为啥BERT要输出512个768呢,原因目前还不清楚,不过现在知道了第一个768(outpu 阅读全文
posted @ 2022-04-19 18:17
Hisi
阅读(456)
评论(0)
推荐(0)
摘要:
Token embeddings: A [CLS] token is added to the input word tokens at the beginning of the first sentence and a [SEP] token is inserted at the end of e 阅读全文
posted @ 2022-04-19 17:45
Hisi
阅读(989)
评论(0)
推荐(0)
摘要:
最近在学习英语的时候,刚好发现了这个新知识,立马记下来哈哈哈哈。 Pre-trained language representations can either be context-free or context-based. Context-based representations can t 阅读全文
posted @ 2022-04-19 17:31
Hisi
阅读(166)
评论(0)
推荐(0)
摘要:
感觉会有用,先记录下来,如果大家看了有帮助,深感荣幸,若不幸点开了,万分抱歉。 Instead of predicting the next word in a sequence, BERT makes use of a novel technique called Masked LM (MLM): 阅读全文
posted @ 2022-04-19 17:21
Hisi
阅读(259)
评论(0)
推荐(0)
浙公网安备 33010602011771号