update

.gitignore

@@ -32,6 +32,7 @@ glove.840B.300d.txt
 glove.42B.300d.txt
 glove.twitter.27B.txt
 *CHECKPOINT/
+checkpoints.json
 
 # project main files
 release_note.json

app.py

@@ -22,6 +22,7 @@ from pyabsa.utils.data_utils.dataset_manager import detect_infer_dataset
 
 download_all_available_datasets()
 
+
 def get_atepc_example(dataset):
     task = TaskCodeOption.Aspect_Polarity_Classification
     dataset_file = detect_infer_dataset(atepc_dataset_items[dataset], task)
@@ -83,6 +84,7 @@ def get_acos_example(dataset):
 
 try:
     from pyabsa import AspectTermExtraction as ATEPC
+
     atepc_dataset_items = {dataset.name: dataset for dataset in ATEPC.ATEPCDatasetList()}
     atepc_dataset_dict = {
         dataset.name: get_atepc_example(dataset.name)
@@ -112,11 +114,11 @@ except Exception as e:
 try:
     from pyabsa import ABSAInstruction
 
-    acos_dataset_items = {dataset.name: dataset for dataset in ABSAInstruction.ACOSDatasetList()[:-1]}
+    acos_dataset_items = {dataset.name: dataset for dataset in ABSAInstruction.ACOSDatasetList()}
     acos_dataset_dict = {
-        dataset.name: get_acos_example(dataset.name) for dataset in ABSAInstruction.ACOSDatasetList()[:-1]
+        dataset.name: get_acos_example(dataset.name) for dataset in ABSAInstruction.ACOSDatasetList()
     }
-    quadruple_extractor = ABSAInstruction.ABSAGenerator(checkpoint="multilingual", device=autocuda.auto_cuda())
+    quadruple_extractor = ABSAInstruction.ABSAGenerator("multilingual")
 except Exception as e:
     print(e)
     acos_dataset_items = {}
@@ -154,7 +156,7 @@ def perform_aste_inference(text, dataset):
 
     pred_triplets = pd.DataFrame(result["Triplets"])
     true_triplets = pd.DataFrame(result["True Triplets"])
-    return pred_triplets, true_triplets, "{}".format(text)
+    return pred_triplets, true_triplets, "{}".format(text.split('####')[0])
 
 
 def perform_acos_inference(text, dataset):
@@ -163,33 +165,42 @@ def perform_acos_inference(text, dataset):
             random.randint(0, len(acos_dataset_dict[dataset]) - 1)
         ]
 
-    raw_output = quadruple_extractor.predict(text)
-    outputs = raw_output[0].strip().split(', ')
-    data = {}
-    for output in outputs:
-        for sub_output in output.split('|'):
-            if 'aspect' in sub_output:
-                data['aspect'] = sub_output.split(':')[1]
-            elif 'opinion' in sub_output:
-                data['opinion'] = sub_output.split(':')[1]
-            elif 'sentiment' in sub_output:
-                data['sentiment'] = sub_output.split(':')[1]
-            elif 'polarity' in sub_output:
-                data['polarity'] = sub_output.split(':')[1]
-            elif 'category' in sub_output:
-                try:
-                    data['category'] = sub_output.split(':')[1]
-                except:
-                    data['category'] = ''
-
-    result = pd.DataFrame.from_dict(data, orient='index').T
+    raw_output = quadruple_extractor.predict(text.split('####')[0], max_length=128)
+
+    result = raw_output['Quadruples']
+    result = pd.DataFrame(result)
     return result, text
 
+
 demo = gr.Blocks()
 
 with demo:
+    with gr.Row():
+
+        if quadruple_extractor:
+            with gr.Row():
+                with gr.Column():
+                    gr.Markdown("# <p align='center'> ABSA Quadruple Extraction (Experimental) </p>")
+
+                    acos_input_sentence = gr.Textbox(
+                        placeholder="Leave this box blank and choose a dataset will give you a random example...",
+                        label="Example:",
+                    )
+                    acos_dataset_ids = gr.Radio(
+                        choices=[dataset.name for dataset in ABSAInstruction.ACOSDatasetList()],
+                        value="Laptop14",
+                        label="Datasets",
+                    )
+                    acos_inference_button = gr.Button("Let's go!")
 
+                    acos_output_text = gr.TextArea(label="Example:")
+                    acos_output_pred_df = gr.DataFrame(label="Predicted Triplets:")
 
+                    acos_inference_button.click(
+                        fn=perform_acos_inference,
+                        inputs=[acos_input_sentence, acos_dataset_ids],
+                        outputs=[acos_output_pred_df, acos_output_text],
+                    )
     with gr.Row():
         if triplet_extractor:
             with gr.Column():
@@ -249,30 +260,7 @@ with demo:
                             inputs=[atepc_input_sentence, atepc_dataset_ids],
                             outputs=[atepc_output_df, atepc_output_text],
                         )
-        if quadruple_extractor:
-            with gr.Row():
-                with gr.Column():
-                    gr.Markdown("# <p align='center'>Aspect Category Opinion Sentiment Extraction !</p>")
 
-                    acos_input_sentence = gr.Textbox(
-                        placeholder="Leave this box blank and choose a dataset will give you a random example...",
-                        label="Example:",
-                    )
-                    acos_dataset_ids = gr.Radio(
-                        choices=[dataset.name for dataset in ABSAInstruction.ACOSDatasetList()],
-                        value="Restaurant16",
-                        label="Datasets",
-                    )
-                    acos_inference_button = gr.Button("Let's go!")
-
-                    acos_output_text = gr.TextArea(label="Example:")
-                    acos_output_pred_df = gr.DataFrame(label="Predicted Triplets:")
-
-                    acos_inference_button.click(
-                        fn=perform_acos_inference,
-                        inputs=[acos_input_sentence, acos_dataset_ids],
-                        outputs=[acos_output_pred_df, acos_output_text],
-                    )
     gr.Markdown(
         """### GitHub Repo: [PyABSA V2](https://github.com/yangheng95/PyABSA)
         ### Author: [Heng Yang](https://github.com/yangheng95) (杨恒)

checkpoints.json

@@ -1 +0,0 @@
-{"2.0.0": {"APC": {"multilingual": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_bert_Multilingual_acc_87.18_f1_83.11.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual2": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_bert_Multilingual_acc_82.66_f1_82.06.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lsa_t_v2_English_acc_82.21_f1_81.81.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LSA-T-V2-Deberta", "Training Dataset": "APCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lsa_t_v2_Chinese_acc_96.0_f1_95.1.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ATEPC": {"multilingual": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_85.1_apcf1_80.2_atef1_76.45.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual-original": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_80.81_apcf1_73.75_atef1_76.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual2": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ABSADatasets.Multilingual", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "fast_lcf_atepc_Multilingual_cdw_apcacc_78.08_apcf1_77.81_atef1_75.41.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.English", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_English_cdw_apcacc_82.36_apcf1_81.89_atef1_75.43.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "chinese": {"id": "", "Training Model": "FAST-LCF-ATEPC", "Training Dataset": "ATEPCDatasetList.Chinese", "Language": "Chinese", "Description": "Trained on RTX3090", "Available Version": "1.10.5+", "Checkpoint File": "fast_lcf_atepc_Chinese_cdw_apcacc_96.22_apcf1_95.32_atef1_78.73.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "RNAC": {"degrad_lstm": {"id": "", "Training Model": "LSTM", "Training Dataset": "ABSADatasets.Multilingual", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "degrad_bert": {"id": "", "Training Model": "MLP", "Training Dataset": "Degrad", "Language": "RNA", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_degrad_acc_87.44_f1_86.99.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "TAD": {"tad-sst2": {"id": "", "Training Model": "TAD", "Training Dataset": "SST2", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-SST2.zip", "Author": "H, Yang (yangheng@m.scnu.edu.cn)"}, "tad-agnews10k": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-AGNews10K.zip", "Author": "H, Yang (yangheng@m.scnu.edu.cn)"}, "tad-amazon": {"id": "", "Training Model": "TAD", "Training Dataset": "AGNews", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "1.15+", "Checkpoint File": "TAD-Amazon.zip", "Author": "H, Yang (yangheng@m.scnu.edu.cn)"}}, "CDD": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "Promise", "Language": "Code", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "bert_mlp_all_cpdp_acc_75.33_f1_73.52.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ASTE": {"english1": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN_SemEval_f1_74.01.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "english": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval", "Language": "English", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "ASTE-EMCGCN_SemEval_f1_74.71.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}, "multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.1+", "Checkpoint File": "EMCGCN-Multilingual-f1_51.95.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "ACOS": {"multilingual": {"id": "", "Training Model": "DeBERTa-v3-Base", "Training Dataset": "SemEval + Synthetic + Chinese_Zhang datasets", "Language": "Multilingual", "Description": "Trained on RTX3090", "Available Version": "2.1.8+", "Checkpoint File": "ACOS.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}, "UPPERTASKCODE": {"promise": {"id": "", "Training Model": "CodeT5-small", "Training Dataset": "DatasetName", "Language": "", "Description": "Trained on RTX3090", "Available Version": "1.16.0+", "Checkpoint File": "lstm_degrad_acc_85.26_f1_84.62.zip", "Author": "H, Yang (hy345@exeter.ac.uk)"}}}}

checkpoints/Multilingual/ACOS/multilingual-acos.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7e6f53b721579e10fab9d82ff085caf051a6917dcd7d2ec9a4d00a8c44c8d0
-size 882150443
+oid sha256:550bd9d9c5c82b8e34236a3819b70fd2da3e8b1058566ca15ae1f2a4190a5486
+size 920064620

emergency_notification.txt

@@ -1,5 +1,6 @@
 
 [New Feature] Aspect Sentiment Triplet Extraction from v2.1.0 test version (https://github.com/yangheng95/PyABSA/tree/v2/examples-v2/aspect_sentiment_triplet_extration)
+[New Feature] Aspect CategoryOpinion Sentiment Quadruple Extraction from v2.2.0 test version (https://github.com/yangheng95/PyABSA/tree/v2/examples-v2/aspect_opinion_sentiment_category_extraction)
 
 If you find any problems, please report them on GitHub. Thanks!
 The v2.x versions are not compatible with Google Colab. Please downgrade to 1.16.27.

requirements.txt

@@ -1 +1 @@
-pyabsa>=2.1.4
+pyabsa>=2.1.12