NLP
发布于 2023-02-13
CS224N Lecture 10: Transformers and Pretraining
Subword Modeling 在之前的学习中,我们都以有限的词汇作为基本假设来训练模型。在遇到“字典”里没出现过的词语时,我们 …
发布于 2023-02-13
CS224N Lecture 9: Self-Attention and Transformers
Issues with RNN models Linear interaction distance: words that sh …
发布于 2023-02-06
pack_padded_sequence 与 pad_packed_sequence
为了提高效率,模型在处理句子(embeddings)时并不是一句一句进行的,而是以 batch 为单位批量处理。但一个 batch …
发布于 2023-02-06
CS224N Lecture 7: Translation, Seq2Seq, Attention
For language which there isn’t much parallel data available, comm …
发布于 2023-02-06
CS224N Lecture 6: Simple and LSTM RNNs
Training a RNN Language Model At each step, the model have the pr …
发布于 2023-01-16
CS224N Lecture 4: Syntactic Structure and Dependency Parsing
Context-Free Grammars (CFGs) Also called constituency or phrases …