megantosh's picture
Update README.md
6cdd2d5
---
language: ar
license: apache-2.0
datasets:
- AQMAR
---
# Arabic NER Model using Flair Embeddings
Training was conducted over 94 epochs, using a linear decaying learning rate of 2e-05, and a total batch size of 32.
11
12
Results:
- F1-score (micro) 0.8666
- F1-score (macro) 0.8488
By class:
LOC tp: 539 - fp: 51 - fn: 68 - precision: 0.9136 - recall: 0.8880 - f1-score: 0.9006
MISC tp: 408 - fp: 57 - fn: 89 - precision: 0.8774 - recall: 0.8209 - f1-score: 0.8482
ORG tp: 167 - fp: 43 - fn: 64 - precision: 0.7952 - recall: 0.7229 - f1-score: 0.7574
PER tp: 501 - fp: 65 - fn: 60 - precision: 0.8852 - recall: 0.8930 - f1-score: 0.8891
---
```
2020-10-27 12:05:47,801 Model: "SequenceTagger(
(embeddings): StackedEmbeddings(
(list_embedding_0): WordEmbeddings('glove')
(list_embedding_1): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(7125, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=7125, bias=True)
)
)
(list_embedding_2): FlairEmbeddings(
(lm): LanguageModel(
(drop): Dropout(p=0.1, inplace=False)
(encoder): Embedding(7125, 100)
(rnn): LSTM(100, 2048)
(decoder): Linear(in_features=2048, out_features=7125, bias=True)
)
)
)
(word_dropout): WordDropout(p=0.05)
(locked_dropout): LockedDropout(p=0.5)
(embedding2nn): Linear(in_features=4196, out_features=4196, bias=True)
(rnn): LSTM(4196, 256, batch_first=True, bidirectional=True)
(linear): Linear(in_features=512, out_features=15, bias=True)
(beta): 1.0
(weights): None
(weight_tensor) None
```