Update README.md
Browse files
README.md
CHANGED
@@ -10,10 +10,9 @@ widget:
|
|
10 |
|
11 |
# POET: A French Extended Part-of-Speech Tagger
|
12 |
|
13 |
-
- Corpora: [
|
14 |
-
- Model: [Flair](https://www.aclweb.org/anthology/C18-1139.pdf)
|
15 |
- Embeddings: [FastText](https://fasttext.cc/)
|
16 |
-
- Sequence Labelling: [LSTM-CRF](https://arxiv.org/abs/1011.4088)
|
17 |
- Number of Epochs: 115
|
18 |
|
19 |
**People Involved**
|
@@ -52,13 +51,13 @@ Output:
|
|
52 |
|
53 |
## Training data
|
54 |
|
55 |
-
`
|
56 |
|
57 |
Originally, the corpora consists of 400,399 words (16,341 sentences) and had 17 different classes. Now, after applying our tags augmentation we obtain 60 different classes which add linguistic and semantic information such as the gender, number, mood, person, tense or verb form given in the different CoNLL-03 fields from the original corpora.
|
58 |
|
59 |
We based our tags on the level of details given by the [LIA_TAGG](http://pageperso.lif.univ-mrs.fr/frederic.bechet/download.html) statistical POS tagger written by [Frédéric Béchet](http://pageperso.lif.univ-mrs.fr/frederic.bechet/index-english.html) in 2001.
|
60 |
|
61 |
-
The corpora used for this model is available on [Github](https://github.com/qanastek/
|
62 |
|
63 |
Training data are fed to the model as free language and doesn't pass a normalization phase. Thus, it's made the model case and punctuation sensitive.
|
64 |
|
@@ -138,7 +137,7 @@ PRON VERB SCONJ ADP CCONJ DET NOUN ADJ AUX ADV PUNCT PROPN NUM SYM PART X INTJ
|
|
138 |
|
139 |
## Evaluation results
|
140 |
|
141 |
-
The test corpora used for this evaluation is available on [Github](https://github.com/qanastek/
|
142 |
|
143 |
```plain
|
144 |
Results:
|
|
|
10 |
|
11 |
# POET: A French Extended Part-of-Speech Tagger
|
12 |
|
13 |
+
- Corpora: [ANTILLES](https://github.com/qanastek/ANTILLES)
|
|
|
14 |
- Embeddings: [FastText](https://fasttext.cc/)
|
15 |
+
- Sequence Labelling: [Bi-LSTM-CRF](https://arxiv.org/abs/1011.4088)
|
16 |
- Number of Epochs: 115
|
17 |
|
18 |
**People Involved**
|
|
|
51 |
|
52 |
## Training data
|
53 |
|
54 |
+
`ANTILLES` is a part-of-speech tagging corpora based on [UD_French-GSD](https://universaldependencies.org/treebanks/fr_gsd/index.html) which was originally created in 2015 and is based on the [universal dependency treebank v2.0](https://github.com/ryanmcd/uni-dep-tb).
|
55 |
|
56 |
Originally, the corpora consists of 400,399 words (16,341 sentences) and had 17 different classes. Now, after applying our tags augmentation we obtain 60 different classes which add linguistic and semantic information such as the gender, number, mood, person, tense or verb form given in the different CoNLL-03 fields from the original corpora.
|
57 |
|
58 |
We based our tags on the level of details given by the [LIA_TAGG](http://pageperso.lif.univ-mrs.fr/frederic.bechet/download.html) statistical POS tagger written by [Frédéric Béchet](http://pageperso.lif.univ-mrs.fr/frederic.bechet/index-english.html) in 2001.
|
59 |
|
60 |
+
The corpora used for this model is available on [Github](https://github.com/qanastek/ANTILLES) at the [CoNLL-U format](https://universaldependencies.org/format.html).
|
61 |
|
62 |
Training data are fed to the model as free language and doesn't pass a normalization phase. Thus, it's made the model case and punctuation sensitive.
|
63 |
|
|
|
137 |
|
138 |
## Evaluation results
|
139 |
|
140 |
+
The test corpora used for this evaluation is available on [Github](https://github.com/qanastek/ANTILLES/blob/main/ANTILLES/test.conllu).
|
141 |
|
142 |
```plain
|
143 |
Results:
|