finiteautomata commited on
Commit
e13f6ff
1 Parent(s): 81d7c83

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Targeted Sentiment Analysis in News Headlines
2
+
3
+ BERT classifier fine-tuned in a news headlines dataset annotated for target polarity.
4
+
5
+ (details to be published)
6
+
7
+
8
+ ## Examples
9
+
10
+ Input is as follows
11
+
12
+ `Headline [SEP] Target`
13
+
14
+ where headline is the news title and target an
15
+
16
+ Try
17
+
18
+ `Alberto Fernández: "El gobierno de Macri fue un desastre" [SEP] Macri` (should be NEG)
19
+
20
+ and
21
+
22
+ `Alberto Fernández: "El gobierno de Macri fue un desastre" [SEP] Macri` (POS or NEU)
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "NEG",
13
+ "1": "NEU",
14
+ "2": "POS"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NEG": 0,
20
+ "NEU": 1,
21
+ "POS": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "transformers_version": "4.4.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 31002
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0790a8e35007b467b4086394d155b9d6980622fbe4001d424244c181527c680
3
+ size 439500425
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/jmperez/.cache/huggingface/transformers/78141ed1e8dcc5ff370950397ca0d1c5c9da478f54ec14544187d8a93eff1a26.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "name_or_path": "dccuchile/bert-base-spanish-wwm-uncased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff