zhenpingli/multi-head-selft-attention-lstm zhenpingli/multi-head-selft-attention-lstm

  • Stars
    star
    15
  • Rank 1,365,014 (Top 27 %)
  • Language
    Python
  • Created over 3 years ago
  • Updated over 3 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
zhenpingli/multi-head-selft-attention-lstm
github

zhenpingli

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

在sts数据集上用多头注意力机制上进行测试。 pytorch torchtext 代码简练，非常适合新手了解多头注意力机制的运作。不想transformer牵扯很多层 multi-head attention + one layer lstm

More Repositories

1

KGEL

Multi-hop Question Generation with Knowledge Graph-enhanced Language Model
Python
6
star
2

transformer-with-annotation

transformer translation with annotation
Python
5
star
3

auto_write_novel

自动依据小四小说生成新的小说
Python
5
star
4

seq2seq_attention_numpy

use numpy implement the attetion model
Python
2
star
5

numpy-lstm-

Jupyter Notebook
2
star
6

torchtext_demo

Python
2
star
7

seq2seq_attention

numpy attention
Python
2
star
8

numpy_gru

use the numpy to code the Gru RNN network step by step
Python
2
star
9

entity-identification-dilated-conv-

entity identification dilated conv CNN 医药实体识别 Tensorflow Medical entity identification
Python
2
star
10

Guiding-the-Growth-Difficulty-Controllable-Question-Generation-through-Step-by-Step-Rewriting

Second collation of paper <Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting>
1
star
11

neural-network

1
star
12

pytorch-openai-transformer-lm-master

this is a base structure of gpt ,for easy to understand withou complex frame
Python
1
star
13

argument-generation

Python
1
star
14

beam_search

beam_search 算法python 版本，便于在pytorch中进行更改，优点是可以使用batch_size=1，对于复杂架构的input格式不用repeat数据
Python
1
star
15

back-propagation-iris

Python
1
star
16

Dneural-argument-generation-maste

1
star
17

flexible-bp-network

Python
1
star