MichaelHuang
/

muril_base_cased_urdu_ner_2.0

Token Classification

Model card Files Files and versions

MichaelHuang commited on May 26, 2023

Commit

aac1ba1

·

1 Parent(s): 0e7e791

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -8,10 +8,10 @@ tags:
 # NER in Urdu
 ## muril_base_cased_urdu_ner_2.0
-Besides the same base model and the NER dataset used for muril_base_cased_urdu_ner, I added a novel politics NER dataset translated from [CrossNER](https://github.com/zliucr/CrossNER/tree/main)
 Since the additional dataset was small, the new labels may not be recognized effectively; however, the overall performance of recognizing the original 22 labels has increased compared to muril_base_cased_urdu_ner.
-Base model is [google/muril-base-cased](https://huggingface.co/google/muril-base-cased), a BERT model pre-trained on 17 Indian languages and their transliterated counterparts.
 The main Urdu NER dataset is translated from the Hindi NER dataset from [HiNER](https://github.com/cfiltnlp/HiNER).
 ## Usage

 # NER in Urdu
 ## muril_base_cased_urdu_ner_2.0
+Besides the same base model and the NER dataset used for muril_base_cased_urdu_ner, I added a novel politics NER dataset translated from [CrossNER](https://github.com/zliucr/CrossNER/tree/main).
 Since the additional dataset was small, the new labels may not be recognized effectively; however, the overall performance of recognizing the original 22 labels has increased compared to muril_base_cased_urdu_ner.
+The base model is [google/muril-base-cased](https://huggingface.co/google/muril-base-cased), a BERT model pre-trained on 17 Indian languages and their transliterated counterparts.
 The main Urdu NER dataset is translated from the Hindi NER dataset from [HiNER](https://github.com/cfiltnlp/HiNER).
 ## Usage