Update README.md

README.md

@@ -74,7 +74,7 @@ tokenizer_hf = AutoTokenizer.from_pretrained('projecte-aina/roberta-base-ca-v2')
 model = AutoModelForMaskedLM.from_pretrained('projecte-aina/roberta-base-ca-v2')
 model.eval()
 pipeline = FillMaskPipeline(model, tokenizer_hf)
-text = f"Em dic <mask>."
+text = f"Em dic <mask>."137,775
 res_hf = pipeline(text)
 pprint([r['token_str'] for r in res_hf])
 ```
@@ -131,18 +131,17 @@ It contains the following tasks and their related datasets:
 
  3. Text Classification (TC)
      
-    **[TeCla](https://huggingface.co/datasets/projecte-aina/tecla)**: consisting of 137k news pieces from the Catalan News Agency ([ACN](https://www.acn.cat/)) corpus, with 30 labels
+    **[TeCla](https://huggingface.co/datasets/projecte-aina/tecla)**: consisting of 137k news pieces from the Catalan News Agency ([ACN](https://www.acn.cat/)) corpus, with 30 labels.
 
- 3. Text Classification (TC)
+ 4. Textual Entailment (TE)
      
-    **[TeCla](https://huggingface.co/datasets/projecte-aina/tecla)**: consisting of 137k news pieces from the Catalan News Agency ([ACN](https://www.acn.cat/)) corpus, with 30 labels
+    **[TeCa](https://huggingface.co/datasets/projecte-aina/teca)**: consisting of 21,163 pairs of premises and hypotheses, annotated according to the inference relation they have (implication, contradiction, or neutral), extracted from the [Catalan Textual Corpus](https://huggingface.co/datasets/projecte-aina/catalan_textual_corpus).
 
- 4. Semantic Textual Similarity (STS)
+ 5. Semantic Textual Similarity (STS)
     
-    **[Catalan semantic textual similarity](https://huggingface.co/datasets/projecte-aina/sts-ca)**: consisting of more than 3000 sentence pairs, annotated with the semantic similarity between them, 
-    scraped from the [Catalan Textual Corpus](https://huggingface.co/datasets/projecte-aina/catalan_textual_corpus)
+    **[Catalan semantic textual similarity](https://huggingface.co/datasets/projecte-aina/sts-ca)**: consisting of more than 3000 sentence pairs, annotated with the semantic similarity between them, scraped from the [Catalan Textual Corpus](https://huggingface.co/datasets/projecte-aina/catalan_textual_corpus).
 
- 5. Question Answering (QA):
+ 6. Question Answering (QA):
     
     **[VilaQuAD](https://huggingface.co/datasets/projecte-aina/vilaquad)**: contains 6,282 pairs of questions and answers, outsourced from 2095 Catalan language articles from VilaWeb newswire text.
     
@@ -150,7 +149,7 @@ It contains the following tasks and their related datasets:
    
     **[CatalanQA](https://huggingface.co/datasets/projecte-aina/catalanqa)**: an aggregation of 2 previous datasets (VilaQuAD and ViquiQuAD), 21,427 pairs of Q/A balanced by type of question, containing one question and one answer per context, although the contexts can repeat multiple times.
     
-    **[XQuAD](https://huggingface.co/datasets/projecte-aina/xquad-ca)**: the Catalan translation of XQuAD, a multilingual collection of manual translations of 1,190 question-answer pairs from English Wikipedia used only as a _test set_
+    **[XQuAD](https://huggingface.co/datasets/projecte-aina/xquad-ca)**: the Catalan translation of XQuAD, a multilingual collection of manual translations of 1,190 question-answer pairs from English Wikipedia used only as a _test set_.
     
 Here are the train/dev/test splits of the datasets:
 
@@ -160,13 +159,14 @@ Here are the train/dev/test splits of the datasets:
 | POS (Ancora)| 16,678 | 13,123 | 1,709 | 1,846 |
 | STS         | 3,073 | 2,073 | 500 | 500 |
 | TC (TeCla) |  137,775 | 110,203 | 13,786 |  13,786|
+| TE (TeCa) |  21,163 | 16,930 | 2,116 | 2,117
 | QA (VilaQuAD) | 6,282  | 3,882  | 1,200  | 1,200 |
 | QA (ViquiQuAD) | 14,239  | 11,255  | 1,492  | 1,429 |
 | QA (CatalanQA) | 21,427  | 17,135  | 2,157  | 2,135 |
 
 ### Evaluation Results
 
-| Task        | NER (F1)      | POS (F1)   | STS (Combined)   | TC (Acc.) | TE (Acc.) | QA (Vilaquad) (F1/EM)| QA (ViquiQuAD) (F1/EM) | QA (CatalanQA) (F1/EM) | QA (XQuAD-Ca)<sup>1</sup> (F1/EM) | 
+| Task        | NER (F1)      | POS (F1)   | STS (Comb)   | TC (Acc.) | TE (Acc.) | QA (Vilaquad) (F1/EM)| QA (ViquiQuAD) (F1/EM) | QA (CatalanQA) (F1/EM) | QA (XQuAD-Ca)<sup>1</sup> (F1/EM) | 
 | ------------|:-------------:| -----:|:------|:------|:-------|:------|:----|:----|:----|
 | RoBERTa-base-ca-v2      | **89.45** | 99.09 | 79.07 | **74.26** | **83.14** | **87.74/72.58** | **88.72/75.91** | **89.50**/76.63 | **73.64/55.42** |
 | BERTa      | 88.94 | **99.10** | **80.19** | 73.65 | 79.26 | 85.93/70.58 | 87.12/73.11 | 89.17/**77.14** | 69.20/51.47 |