fastNLP/reproduction
2019-06-05 11:05:46 +08:00
..
Biaffine_parser Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
Char-aware_NLM remove unused codes; add more tests 2018-10-07 15:03:00 +08:00
Chinese_word_segmentation Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
CNN-sentence_classification * fixing unit tests 2018-11-27 22:22:19 +08:00
HAN-document_classification optimize CWS example 2018-08-31 11:23:40 +08:00
LSTM+self_attention_sentiment_analysis Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
matching firstly add matching in reproduction 2019-06-05 01:01:30 +08:00
POS_tagging Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
seqence_labelling/cws 序列标注的SemiCRFRelay中文分词. 2019-06-04 23:40:46 +08:00
Star_transformer Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
text_classification add text_classification reproduction dir 2019-06-05 11:05:46 +08:00
__init__.py 1. 将pad的功能从FieldArray中剥离出来,使用Padder完成各种padding操作。 2019-01-15 22:21:55 +08:00
README.md Dev0.4.0 (#149) 2019-05-22 18:43:56 +08:00
utils.py 序列标注的SemiCRFRelay中文分词. 2019-06-04 23:40:46 +08:00

模型复现

这里复现了在fastNLP中实现的模型旨在达到与论文中相符的性能。

复现的模型有:

  • Star-Transformer
  • ...

Star-Transformer

reference

Performance (still in progress)

任务 数据集 SOTA 模型表现
Pos Tagging CTB 9.0 - ACC 92.31
Pos Tagging CONLL 2012 - ACC 96.51
Named Entity Recognition CONLL 2012 - F1 85.66
Text Classification SST - 49.18
Natural Language Inference SNLI - 83.76

Usage

# for sequence labeling(ner, pos tagging, etc)
from fastNLP.models.star_transformer import STSeqLabel
model = STSeqLabel(
    vocab_size=10000, num_cls=50,
    emb_dim=300)


# for sequence classification
from fastNLP.models.star_transformer import STSeqCls
model = STSeqCls(
    vocab_size=10000, num_cls=50,
    emb_dim=300)


# for natural language inference
from fastNLP.models.star_transformer import STNLICls
model = STNLICls(
    vocab_size=10000, num_cls=50,
    emb_dim=300)

...