Upload 8 files

.gitattributes

@@ -1,35 +1,16 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,91 @@
 ---
-license: apache-2.0
+language: 
+- es
+
+tags:
+- Emotion Analysis
+
 ---
+
+**Note**: This model & model card are based on the [finetuned XLM-T for Sentiment Analysis](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment)
+
+# twitter-XLM-roBERTa-base for Emotion Analysis
+This is a XLM-roBERTa-base model trained on ~198M tweets and finetuned for emotion analysis on Spanish language. This model was presented to EmoEvalEs competition, part of [IberLEF 2021 Conference](https://sites.google.com/view/iberlef2021/), where the proposed task was the classification of Spanish tweets between seven different classes: *anger*, *disgust*, *fear*, *joy*, *sadness*, *surprise*, and *other*. We achieved the first position in the competition with a macro-averaged F1 score of 71.70%. 
+- [Our code for EmoEvalEs submission](https://github.com/gsi-upm/emoevales-iberlef2021).
+- [EmoEvalEs Dataset](https://github.com/pendrag/EmoEvalEs)
+## Example Pipeline with a [Tweet from @JaSantaolalla](https://twitter.com/JaSantaolalla/status/1398383243645177860)
+```python
+from transformers import pipeline
+model_path = "daveni/twitter-xlm-roberta-emotion-es"
+emotion_analysis = pipeline("text-classification", framework="pt", model=model_path, tokenizer=model_path)
+emotion_analysis("Einstein dijo: Solo hay dos cosas infinitas, el universo y los pinches anuncios de bitcoin en Twitter. Paren ya carajo aaaaaaghhgggghhh me quiero murir")
+```
+```
+[{'label': 'anger', 'score': 0.48307016491889954}]
+```
+## Full classification example
+```python
+from transformers import AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoConfig
+import numpy as np
+from scipy.special import softmax
+# Preprocess text (username and link placeholders)
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    return " ".join(new_text)
+model_path = "daveni/twitter-xlm-roberta-emotion-es"
+tokenizer = AutoTokenizer.from_pretrained(model_path )
+config = AutoConfig.from_pretrained(model_path )
+# PT
+model = AutoModelForSequenceClassification.from_pretrained(model_path )
+text = "Se ha quedao bonito día para publicar vídeo, ¿no? Hoy del tema más diferente que hemos tocado en el canal."
+text = preprocess(text)
+print(text)
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+scores = output[0][0].detach().numpy()
+scores = softmax(scores)
+# Print labels and scores
+ranking = np.argsort(scores)
+ranking = ranking[::-1]
+for i in range(scores.shape[0]):
+    l = config.id2label[ranking[i]]
+    s = scores[ranking[i]]
+    print(f"{i+1}) {l} {np.round(float(s), 4)}")
+```
+Output: 
+
+```
+Se ha quedao bonito día para publicar vídeo, ¿no? Hoy del tema más diferente que hemos tocado en el canal.
+1) joy 0.7887
+2) others 0.1679
+3) surprise 0.0152
+4) sadness 0.0145
+5) anger 0.0077
+6) disgust 0.0033
+7) fear 0.0027
+```
+
+#### Limitations and bias
+
+- The dataset we used for finetuning was unbalanced, where almost half of the records belonged to the *other* class so there might be bias towards this class.
+
+
+## Training data
+
+Pretrained weights were left identical to the original model released by [cardiffnlp](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base). We used the [EmoEvalEs Dataset](https://github.com/pendrag/EmoEvalEs) for finetuning.
+
+### BibTeX entry and citation info
+
+```bibtex
+@inproceedings{vera2021gsi,
+  title={GSI-UPM at IberLEF2021: Emotion Analysis of Spanish Tweets by Fine-tuning the XLM-RoBERTa Language Model},
+  author={Vera, D and Araque, O and Iglesias, CA},
+  booktitle={Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2021). CEUR Workshop Proceedings, CEUR-WS, M{\'a}laga, Spain},
+  year={2021}
+}
+```

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "./resultsEmotion-preproc/best_model",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "sadness",
+    "1": "joy",
+    "2": "anger",
+    "3": "surprise",
+    "4": "disgust",
+    "5": "fear",
+    "6": "others"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 2,
+    "disgust": 4,
+    "fear": 5,
+    "joy": 1,
+    "others": 6,
+    "sadness": 0,
+    "surprise": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c31580c660db1b7d5b10bfc3595dc7a7d9cdac699e68e25e5e047c904fa35a
+size 1112283849

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-xlm-roberta-base"}