From f78c7f9bdf23b0997fb46c8b3ca2010242f848f0 Mon Sep 17 00:00:00 2001 From: maramhasanain Date: Tue, 5 Sep 2023 10:32:30 +0300 Subject: [PATCH] renamed datasets, assets and tasks for stance and fact. renamed datasets, assets and tasks for stance and fact. --- ...hot.py => Khouja20Factuality_BLOOMZ_ZeroShot.py} | 13 ++++--------- ...Shot.py => Khouja20Factuality_GPT35_ZeroShot.py} | 8 ++++---- ...ewShot.py => Khouja20Factuality_GPT4_FewShot.py} | 8 ++++---- ...oShot.py => Khouja20Factuality_GPT4_ZeroShot.py} | 8 ++++---- ...ot.py => UnifiedFCFactuality_BLOOMZ_ZeroShot.py} | 13 ++++--------- ...wShot.py => UnifiedFCFactuality_GPT4_FewShot.py} | 8 ++++---- ...Shot.py => UnifiedFCFactuality_GPT4_ZeroShot.py} | 8 ++++---- .../ar/semantics/STS/STSTrack1_BLOOMZ_ZeroShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack1_GPT35_ZeroShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack1_GPT4_FewShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack1_GPT4_ZeroShot.py | 4 ++-- .../ar/semantics/STS/STSTrack2_BLOOMZ_ZeroShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack2_GPT35_ZeroShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack2_GPT4_FewShot.py | 4 ++-- assets/ar/semantics/STS/STSTrack2_GPT4_ZeroShot.py | 4 ++-- ...eroShot.py => Khouja20Stance_BLOOMZ_ZeroShot.py} | 8 ++++---- ...ZeroShot.py => Khouja20Stance_GPT35_ZeroShot.py} | 8 ++++---- ...T4_FewShot.py => Khouja20Stance_GPT4_FewShot.py} | 8 ++++---- ..._ZeroShot.py => Khouja20Stance_GPT4_ZeroShot.py} | 8 ++++---- ...roShot.py => UnifiedFCStance_BLOOMZ_ZeroShot.py} | 8 ++++---- ...eroShot.py => UnifiedFCStance_GPT35_ZeroShot.py} | 8 ++++---- ...4_FewShot.py => UnifiedFCStance_GPT4_FewShot.py} | 8 ++++---- ...ZeroShot.py => UnifiedFCStance_GPT4_ZeroShot.py} | 8 ++++---- ...5_ZeroShot.py => Segmentation_GPT35_ZeroShot.py} | 2 +- ...T4_ZeroShot.py => Segmentation_GPT4_ZeroShot.py} | 0 ...{FactualityKhouja20.py => Khouja20Factuality.py} | 6 ++---- .../{StanceKhouja20.py => Khouja20Stance.py} | 4 ++-- .../{STSArSemEval17Track1.py => SemEval17T1STS.py} | 4 ++-- .../{STSArSemEval17Track2.py => SemEval17T2STS.py} | 4 ++-- ...actualityUnifiedFC.py => UnifiedFCFactuality.py} | 4 ++-- .../{StanceUnifiedFC.py => UnifiedFCStance.py} | 7 ++----- llmebench/datasets/__init__.py | 12 ++++++------ llmebench/tasks/FactualityKhouja20.py | 4 ++-- llmebench/tasks/FactualityUnifiedFC.py | 4 ++-- llmebench/tasks/StanceKhouja20.py | 4 ++-- llmebench/tasks/StanceUnifiedFC.py | 4 ++-- llmebench/tasks/__init__.py | 8 ++++---- 37 files changed, 107 insertions(+), 122 deletions(-) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityKhouja20_BLOOMZ_ZeroShot.py => Khouja20Factuality_BLOOMZ_ZeroShot.py} (86%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityKhouja20_GPT35_ZeroShot.py => Khouja20Factuality_GPT35_ZeroShot.py} (87%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityKhouja20_GPT4_FewShot.py => Khouja20Factuality_GPT4_FewShot.py} (92%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityKhouja20_GPT4_ZeroShot.py => Khouja20Factuality_GPT4_ZeroShot.py} (89%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityUnifiedFC_BLOOMZ_ZeroShot.py => UnifiedFCFactuality_BLOOMZ_ZeroShot.py} (85%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityUnifiedFC_GPT4_FewShot.py => UnifiedFCFactuality_GPT4_FewShot.py} (92%) rename assets/ar/factuality_disinformation_harmful_content/factuality/{FactualityUnifiedFC_GPT4_ZeroShot.py => UnifiedFCFactuality_GPT4_ZeroShot.py} (90%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceKhouja20_BLOOMZ_ZeroShot.py => Khouja20Stance_BLOOMZ_ZeroShot.py} (84%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceKhouja20_GPT35_ZeroShot.py => Khouja20Stance_GPT35_ZeroShot.py} (87%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceKhouja20_GPT4_FewShot.py => Khouja20Stance_GPT4_FewShot.py} (93%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceKhouja20_GPT4_ZeroShot.py => Khouja20Stance_GPT4_ZeroShot.py} (90%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceUnifiedFC_BLOOMZ_ZeroShot.py => UnifiedFCStance_BLOOMZ_ZeroShot.py} (87%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceUnifiedFC_GPT35_ZeroShot.py => UnifiedFCStance_GPT35_ZeroShot.py} (90%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceUnifiedFC_GPT4_FewShot.py => UnifiedFCStance_GPT4_FewShot.py} (93%) rename assets/ar/sentiment_emotion_others/stance_detection/{StanceUnifiedFC_GPT4_ZeroShot.py => UnifiedFCStance_GPT4_ZeroShot.py} (91%) rename assets/ar/sequence_tagging_and_information_extraction/segmentation/{segmentation_GPT35_ZeroShot.py => Segmentation_GPT35_ZeroShot.py} (97%) rename assets/ar/sequence_tagging_and_information_extraction/segmentation/{segmentation_GPT4_ZeroShot.py => Segmentation_GPT4_ZeroShot.py} (100%) rename llmebench/datasets/{FactualityKhouja20.py => Khouja20Factuality.py} (90%) rename llmebench/datasets/{StanceKhouja20.py => Khouja20Stance.py} (92%) rename llmebench/datasets/{STSArSemEval17Track1.py => SemEval17T1STS.py} (94%) rename llmebench/datasets/{STSArSemEval17Track2.py => SemEval17T2STS.py} (94%) rename llmebench/datasets/{FactualityUnifiedFC.py => UnifiedFCFactuality.py} (95%) rename llmebench/datasets/{StanceUnifiedFC.py => UnifiedFCStance.py} (95%) diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_BLOOMZ_ZeroShot.py similarity index 86% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_BLOOMZ_ZeroShot.py index 7fd21752..693d311c 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_BLOOMZ_ZeroShot.py @@ -1,20 +1,15 @@ import os -import random -import re -from llmebench.datasets import FactualityKhouja20Dataset +from llmebench.datasets import Khouja20FactualityDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import FactualityKhouja20Task - - -random.seed(1333) +from llmebench.tasks import Khouja20FactualityTask def config(): return { - "dataset": FactualityKhouja20Dataset, + "dataset": Khouja20FactualityDataset, "dataset_args": {}, - "task": FactualityKhouja20Task, + "task": Khouja20FactualityTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT35_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT35_ZeroShot.py similarity index 87% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT35_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT35_ZeroShot.py index 1dceb259..9fdf8648 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT35_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT35_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import FactualityKhouja20Dataset +from llmebench.datasets import Khouja20FactualityDataset from llmebench.models import GPTModel, RandomGPTModel -from llmebench.tasks import FactualityKhouja20Task +from llmebench.tasks import Khouja20FactualityTask def config(): return { - "dataset": FactualityKhouja20Dataset, + "dataset": Khouja20FactualityDataset, "dataset_args": {}, - "task": FactualityKhouja20Task, + "task": Khouja20FactualityTask, "task_args": {}, "model": GPTModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_FewShot.py similarity index 92% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_FewShot.py index 82fb95ef..852d4cb4 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_FewShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import FactualityKhouja20Dataset +from llmebench.datasets import Khouja20FactualityDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import FactualityKhouja20Task +from llmebench.tasks import Khouja20FactualityTask def config(): return { - "dataset": FactualityKhouja20Dataset, + "dataset": Khouja20FactualityDataset, "dataset_args": {}, - "task": FactualityKhouja20Task, + "task": Khouja20FactualityTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_ZeroShot.py similarity index 89% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_ZeroShot.py index add924df..70cc80e3 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityKhouja20_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/Khouja20Factuality_GPT4_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import FactualityKhouja20Dataset +from llmebench.datasets import Khouja20FactualityDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import FactualityKhouja20Task +from llmebench.tasks import Khouja20FactualityTask def config(): return { - "dataset": FactualityKhouja20Dataset, + "dataset": Khouja20FactualityDataset, "dataset_args": {}, - "task": FactualityKhouja20Task, + "task": Khouja20FactualityTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_BLOOMZ_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_BLOOMZ_ZeroShot.py similarity index 85% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_BLOOMZ_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_BLOOMZ_ZeroShot.py index 47d99663..29a0b48a 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_BLOOMZ_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_BLOOMZ_ZeroShot.py @@ -1,20 +1,15 @@ import os -import random -import re -from llmebench.datasets import FactualityUnifiedFCDataset +from llmebench.datasets import UnifiedFCFactualityDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import FactualityUnifiedFCTask - - -random.seed(1333) +from llmebench.tasks import UnifiedFCFactualityTask def config(): return { - "dataset": FactualityUnifiedFCDataset, + "dataset": UnifiedFCFactualityDataset, "dataset_args": {}, - "task": FactualityUnifiedFCTask, + "task": UnifiedFCFactualityTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_FewShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_FewShot.py similarity index 92% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_FewShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_FewShot.py index a85f1182..a7464626 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_FewShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_FewShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import FactualityUnifiedFCDataset +from llmebench.datasets import UnifiedFCFactualityDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import FactualityUnifiedFCTask +from llmebench.tasks import UnifiedFCFactualityTask def config(): return { - "dataset": FactualityUnifiedFCDataset, + "dataset": UnifiedFCFactualityDataset, "dataset_args": {}, - "task": FactualityUnifiedFCTask, + "task": UnifiedFCFactualityTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_ZeroShot.py b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_ZeroShot.py similarity index 90% rename from assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_ZeroShot.py rename to assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_ZeroShot.py index 0c1d21c2..b0ca3020 100644 --- a/assets/ar/factuality_disinformation_harmful_content/factuality/FactualityUnifiedFC_GPT4_ZeroShot.py +++ b/assets/ar/factuality_disinformation_harmful_content/factuality/UnifiedFCFactuality_GPT4_ZeroShot.py @@ -2,9 +2,9 @@ import random import re -from llmebench.datasets import FactualityUnifiedFCDataset +from llmebench.datasets import UnifiedFCFactualityDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import FactualityUnifiedFCTask +from llmebench.tasks import UnifiedFCFactualityTask random.seed(1333) @@ -12,9 +12,9 @@ def config(): return { - "dataset": FactualityUnifiedFCDataset, + "dataset": UnifiedFCFactualityDataset, "dataset_args": {}, - "task": FactualityUnifiedFCTask, + "task": UnifiedFCFactualityTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/semantics/STS/STSTrack1_BLOOMZ_ZeroShot.py b/assets/ar/semantics/STS/STSTrack1_BLOOMZ_ZeroShot.py index 9fd822f1..b2aa9af5 100644 --- a/assets/ar/semantics/STS/STSTrack1_BLOOMZ_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack1_BLOOMZ_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track1Dataset +from llmebench.datasets import SemEval17T1STSDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import STSTrack1Task def config(): return { - "dataset": STSArSemEval17Track1Dataset, + "dataset": SemEval17T1STSDataset, "dataset_args": {}, "task": STSTrack1Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack1_GPT35_ZeroShot.py b/assets/ar/semantics/STS/STSTrack1_GPT35_ZeroShot.py index 1b99e05a..ddb4f0a6 100644 --- a/assets/ar/semantics/STS/STSTrack1_GPT35_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack1_GPT35_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track1Dataset +from llmebench.datasets import SemEval17T1STSDataset from llmebench.models import GPTModel from llmebench.tasks import STSTrack1Task def config(): return { - "dataset": STSArSemEval17Track1Dataset, + "dataset": SemEval17T1STSDataset, "dataset_args": {}, "task": STSTrack1Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack1_GPT4_FewShot.py b/assets/ar/semantics/STS/STSTrack1_GPT4_FewShot.py index aff4ddad..ae33215d 100644 --- a/assets/ar/semantics/STS/STSTrack1_GPT4_FewShot.py +++ b/assets/ar/semantics/STS/STSTrack1_GPT4_FewShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import STSArSemEval17Track1Dataset +from llmebench.datasets import SemEval17T1STSDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import STSTrack1Task def config(): return { - "dataset": STSArSemEval17Track1Dataset, + "dataset": SemEval17T1STSDataset, "dataset_args": {}, "task": STSTrack1Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack1_GPT4_ZeroShot.py b/assets/ar/semantics/STS/STSTrack1_GPT4_ZeroShot.py index 3f94a169..3abd2c4b 100644 --- a/assets/ar/semantics/STS/STSTrack1_GPT4_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack1_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track1Dataset +from llmebench.datasets import SemEval17T1STSDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import STSTrack1Task def config(): return { - "dataset": STSArSemEval17Track1Dataset, + "dataset": SemEval17T1STSDataset, "dataset_args": {}, "task": STSTrack1Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack2_BLOOMZ_ZeroShot.py b/assets/ar/semantics/STS/STSTrack2_BLOOMZ_ZeroShot.py index 9b2e6efe..c0f63c01 100644 --- a/assets/ar/semantics/STS/STSTrack2_BLOOMZ_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack2_BLOOMZ_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track1Dataset +from llmebench.datasets import SemEval17T1STSDataset from llmebench.models import BLOOMPetalModel from llmebench.tasks import STSTrack1Task def config(): return { - "dataset": STSArSemEval17Track1Dataset, + "dataset": SemEval17T1STSDataset, "dataset_args": {}, "task": STSTrack1Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack2_GPT35_ZeroShot.py b/assets/ar/semantics/STS/STSTrack2_GPT35_ZeroShot.py index da4dff44..b93b5313 100644 --- a/assets/ar/semantics/STS/STSTrack2_GPT35_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack2_GPT35_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track2Dataset +from llmebench.datasets import SemEval17T2STSDataset from llmebench.models import GPTModel, RandomGPTModel from llmebench.tasks import STSTrack2Task def config(): return { - "dataset": STSArSemEval17Track2Dataset, + "dataset": SemEval17T2STSDataset, "dataset_args": {}, "task": STSTrack2Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack2_GPT4_FewShot.py b/assets/ar/semantics/STS/STSTrack2_GPT4_FewShot.py index a4e9e840..d0ca3c5a 100644 --- a/assets/ar/semantics/STS/STSTrack2_GPT4_FewShot.py +++ b/assets/ar/semantics/STS/STSTrack2_GPT4_FewShot.py @@ -1,13 +1,13 @@ import os -from llmebench.datasets import STSArSemEval17Track2Dataset +from llmebench.datasets import SemEval17T2STSDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import STSTrack2Task def config(): return { - "dataset": STSArSemEval17Track2Dataset, + "dataset": SemEval17T2STSDataset, "dataset_args": {}, "task": STSTrack2Task, "task_args": {}, diff --git a/assets/ar/semantics/STS/STSTrack2_GPT4_ZeroShot.py b/assets/ar/semantics/STS/STSTrack2_GPT4_ZeroShot.py index 4be3334c..a6ae3f1a 100644 --- a/assets/ar/semantics/STS/STSTrack2_GPT4_ZeroShot.py +++ b/assets/ar/semantics/STS/STSTrack2_GPT4_ZeroShot.py @@ -1,14 +1,14 @@ import os import re -from llmebench.datasets import STSArSemEval17Track2Dataset +from llmebench.datasets import SemEval17T2STSDataset from llmebench.models import GPTChatCompletionModel from llmebench.tasks import STSTrack2Task def config(): return { - "dataset": STSArSemEval17Track2Dataset, + "dataset": SemEval17T2STSDataset, "dataset_args": {}, "task": STSTrack2Task, "task_args": {}, diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_BLOOMZ_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_BLOOMZ_ZeroShot.py similarity index 84% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_BLOOMZ_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_BLOOMZ_ZeroShot.py index 76f29a4d..b4f2bdd0 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_BLOOMZ_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_BLOOMZ_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import StanceKhouja20Dataset +from llmebench.datasets import Khouja20StanceDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import StanceKhouja20Task +from llmebench.tasks import Khouja20StanceTask def config(): return { - "dataset": StanceKhouja20Dataset, + "dataset": Khouja20StanceDataset, "dataset_args": {}, - "task": StanceKhouja20Task, + "task": Khouja20StanceTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT35_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT35_ZeroShot.py similarity index 87% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT35_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT35_ZeroShot.py index d4fbdb93..0313fd46 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT35_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT35_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import StanceKhouja20Dataset +from llmebench.datasets import Khouja20StanceDataset from llmebench.models import GPTModel, RandomGPTModel -from llmebench.tasks import StanceKhouja20Task +from llmebench.tasks import Khouja20StanceTask def config(): return { - "dataset": StanceKhouja20Dataset, + "dataset": Khouja20StanceDataset, "dataset_args": {}, - "task": StanceKhouja20Task, + "task": Khouja20StanceTask, "task_args": {}, "model": GPTModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_FewShot.py b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_FewShot.py similarity index 93% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_FewShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_FewShot.py index 1caa14ef..ac923e21 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_FewShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_FewShot.py @@ -1,16 +1,16 @@ import os import re -from llmebench.datasets import StanceKhouja20Dataset +from llmebench.datasets import Khouja20StanceDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import StanceKhouja20Task +from llmebench.tasks import Khouja20StanceTask def config(): return { - "dataset": StanceKhouja20Dataset, + "dataset": Khouja20StanceDataset, "dataset_args": {}, - "task": StanceKhouja20Task, + "task": Khouja20StanceTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_ZeroShot.py similarity index 90% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_ZeroShot.py index 3958ccb6..0d0229db 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceKhouja20_GPT4_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/Khouja20Stance_GPT4_ZeroShot.py @@ -1,16 +1,16 @@ import os import re -from llmebench.datasets import StanceKhouja20Dataset +from llmebench.datasets import Khouja20StanceDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import StanceKhouja20Task +from llmebench.tasks import Khouja20StanceTask def config(): return { - "dataset": StanceKhouja20Dataset, + "dataset": Khouja20StanceDataset, "dataset_args": {}, - "task": StanceKhouja20Task, + "task": Khouja20StanceTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_BLOOMZ_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_BLOOMZ_ZeroShot.py similarity index 87% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_BLOOMZ_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_BLOOMZ_ZeroShot.py index 9ac0bb5a..840f26f4 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_BLOOMZ_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_BLOOMZ_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import StanceUnifiedFCDataset +from llmebench.datasets import UnifiedFCStanceDataset from llmebench.models import BLOOMPetalModel -from llmebench.tasks import StanceUnifiedFCTask +from llmebench.tasks import UnifiedFCStanceTask def config(): return { - "dataset": StanceUnifiedFCDataset, + "dataset": UnifiedFCStanceDataset, "dataset_args": {}, - "task": StanceUnifiedFCTask, + "task": UnifiedFCStanceTask, "task_args": {}, "model": BLOOMPetalModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT35_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT35_ZeroShot.py similarity index 90% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT35_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT35_ZeroShot.py index 8c0f0568..5ec9020e 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT35_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT35_ZeroShot.py @@ -1,15 +1,15 @@ import os -from llmebench.datasets import StanceUnifiedFCDataset +from llmebench.datasets import UnifiedFCStanceDataset from llmebench.models import GPTModel, RandomGPTModel -from llmebench.tasks import StanceUnifiedFCTask +from llmebench.tasks import UnifiedFCStanceTask def config(): return { - "dataset": StanceUnifiedFCDataset, + "dataset": UnifiedFCStanceDataset, "dataset_args": {}, - "task": StanceUnifiedFCTask, + "task": UnifiedFCStanceTask, "task_args": {}, "model": GPTModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_FewShot.py b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_FewShot.py similarity index 93% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_FewShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_FewShot.py index 3d27a3d5..aefa3edb 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_FewShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_FewShot.py @@ -1,16 +1,16 @@ import os import re -from llmebench.datasets import StanceUnifiedFCDataset +from llmebench.datasets import UnifiedFCStanceDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import StanceUnifiedFCTask +from llmebench.tasks import UnifiedFCStanceTask def config(): return { - "dataset": StanceUnifiedFCDataset, + "dataset": UnifiedFCStanceDataset, "dataset_args": {}, - "task": StanceUnifiedFCTask, + "task": UnifiedFCStanceTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_ZeroShot.py b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_ZeroShot.py similarity index 91% rename from assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_ZeroShot.py rename to assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_ZeroShot.py index a435a768..be75d2f5 100644 --- a/assets/ar/sentiment_emotion_others/stance_detection/StanceUnifiedFC_GPT4_ZeroShot.py +++ b/assets/ar/sentiment_emotion_others/stance_detection/UnifiedFCStance_GPT4_ZeroShot.py @@ -1,16 +1,16 @@ import os import re -from llmebench.datasets import StanceUnifiedFCDataset +from llmebench.datasets import UnifiedFCStanceDataset from llmebench.models import GPTChatCompletionModel -from llmebench.tasks import StanceUnifiedFCTask +from llmebench.tasks import UnifiedFCStanceTask def config(): return { - "dataset": StanceUnifiedFCDataset, + "dataset": UnifiedFCStanceDataset, "dataset_args": {}, - "task": StanceUnifiedFCTask, + "task": UnifiedFCStanceTask, "task_args": {}, "model": GPTChatCompletionModel, "model_args": { diff --git a/assets/ar/sequence_tagging_and_information_extraction/segmentation/segmentation_GPT35_ZeroShot.py b/assets/ar/sequence_tagging_and_information_extraction/segmentation/Segmentation_GPT35_ZeroShot.py similarity index 97% rename from assets/ar/sequence_tagging_and_information_extraction/segmentation/segmentation_GPT35_ZeroShot.py rename to assets/ar/sequence_tagging_and_information_extraction/segmentation/Segmentation_GPT35_ZeroShot.py index d808ce15..4f70041c 100644 --- a/assets/ar/sequence_tagging_and_information_extraction/segmentation/segmentation_GPT35_ZeroShot.py +++ b/assets/ar/sequence_tagging_and_information_extraction/segmentation/Segmentation_GPT35_ZeroShot.py @@ -2,7 +2,7 @@ import re from llmebench.datasets import ArabicSegmentationDataset -from llmebench.models import GPTModel, RandomGPTModel +from llmebench.models import GPTModel from llmebench.tasks import ArabicSegmentationTask diff --git a/assets/ar/sequence_tagging_and_information_extraction/segmentation/segmentation_GPT4_ZeroShot.py b/assets/ar/sequence_tagging_and_information_extraction/segmentation/Segmentation_GPT4_ZeroShot.py similarity index 100% rename from assets/ar/sequence_tagging_and_information_extraction/segmentation/segmentation_GPT4_ZeroShot.py rename to assets/ar/sequence_tagging_and_information_extraction/segmentation/Segmentation_GPT4_ZeroShot.py diff --git a/llmebench/datasets/FactualityKhouja20.py b/llmebench/datasets/Khouja20Factuality.py similarity index 90% rename from llmebench/datasets/FactualityKhouja20.py rename to llmebench/datasets/Khouja20Factuality.py index aaedbb81..af5e2abe 100644 --- a/llmebench/datasets/FactualityKhouja20.py +++ b/llmebench/datasets/Khouja20Factuality.py @@ -1,11 +1,9 @@ -import pandas as pd - from llmebench.datasets.dataset_base import DatasetBase -class FactualityKhouja20Dataset(DatasetBase): +class Khouja20FactualityDataset(DatasetBase): def __init__(self, **kwargs): - super(FactualityKhouja20Dataset, self).__init__(**kwargs) + super(Khouja20FactualityDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/StanceKhouja20.py b/llmebench/datasets/Khouja20Stance.py similarity index 92% rename from llmebench/datasets/StanceKhouja20.py rename to llmebench/datasets/Khouja20Stance.py index 025fa8af..5be7c387 100644 --- a/llmebench/datasets/StanceKhouja20.py +++ b/llmebench/datasets/Khouja20Stance.py @@ -1,9 +1,9 @@ from llmebench.datasets.dataset_base import DatasetBase -class StanceKhouja20Dataset(DatasetBase): +class Khouja20StanceDataset(DatasetBase): def __init__(self, **kwargs): - super(StanceKhouja20Dataset, self).__init__(**kwargs) + super(Khouja20StanceDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/STSArSemEval17Track1.py b/llmebench/datasets/SemEval17T1STS.py similarity index 94% rename from llmebench/datasets/STSArSemEval17Track1.py rename to llmebench/datasets/SemEval17T1STS.py index a08f0ffb..e5412f4f 100644 --- a/llmebench/datasets/STSArSemEval17Track1.py +++ b/llmebench/datasets/SemEval17T1STS.py @@ -1,9 +1,9 @@ from llmebench.datasets.dataset_base import DatasetBase -class STSArSemEval17Track1Dataset(DatasetBase): +class SemEval17T1STSDataset(DatasetBase): def __init__(self, **kwargs): - super(STSArSemEval17Track1Dataset, self).__init__(**kwargs) + super(SemEval17T1STSDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/STSArSemEval17Track2.py b/llmebench/datasets/SemEval17T2STS.py similarity index 94% rename from llmebench/datasets/STSArSemEval17Track2.py rename to llmebench/datasets/SemEval17T2STS.py index 4f08e183..8b916880 100644 --- a/llmebench/datasets/STSArSemEval17Track2.py +++ b/llmebench/datasets/SemEval17T2STS.py @@ -1,9 +1,9 @@ from llmebench.datasets.dataset_base import DatasetBase -class STSArSemEval17Track2Dataset(DatasetBase): +class SemEval17T2STSDataset(DatasetBase): def __init__(self, **kwargs): - super(STSArSemEval17Track2Dataset, self).__init__(**kwargs) + super(SemEval17T2STSDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/FactualityUnifiedFC.py b/llmebench/datasets/UnifiedFCFactuality.py similarity index 95% rename from llmebench/datasets/FactualityUnifiedFC.py rename to llmebench/datasets/UnifiedFCFactuality.py index bffe9b22..672c4907 100644 --- a/llmebench/datasets/FactualityUnifiedFC.py +++ b/llmebench/datasets/UnifiedFCFactuality.py @@ -1,9 +1,9 @@ from llmebench.datasets.dataset_base import DatasetBase -class FactualityUnifiedFCDataset(DatasetBase): +class UnifiedFCFactualityDataset(DatasetBase): def __init__(self, **kwargs): - super(FactualityUnifiedFCDataset, self).__init__(**kwargs) + super(UnifiedFCFactualityDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/StanceUnifiedFC.py b/llmebench/datasets/UnifiedFCStance.py similarity index 95% rename from llmebench/datasets/StanceUnifiedFC.py rename to llmebench/datasets/UnifiedFCStance.py index f4365acc..0e478261 100644 --- a/llmebench/datasets/StanceUnifiedFC.py +++ b/llmebench/datasets/UnifiedFCStance.py @@ -1,14 +1,11 @@ import json -import os - -import pandas as pd from llmebench.datasets.dataset_base import DatasetBase -class StanceUnifiedFCDataset(DatasetBase): +class UnifiedFCStanceDataset(DatasetBase): def __init__(self, **kwargs): - super(StanceUnifiedFCDataset, self).__init__(**kwargs) + super(UnifiedFCStanceDataset, self).__init__(**kwargs) def metadata(): return { diff --git a/llmebench/datasets/__init__.py b/llmebench/datasets/__init__.py index 3730d712..c985522b 100644 --- a/llmebench/datasets/__init__.py +++ b/llmebench/datasets/__init__.py @@ -19,8 +19,8 @@ from .CT22Harmful import CT22HarmfulDataset from .CT23Subjectivity import CT23SubjectivityDataset from .Emotion import EmotionDataset -from .FactualityKhouja20 import FactualityKhouja20Dataset -from .FactualityUnifiedFC import FactualityUnifiedFCDataset +from .Khouja20Factuality import Khouja20FactualityDataset +from .UnifiedFCFactuality import UnifiedFCFactualityDataset from .Lemmatization import LemmatizationDataset from .Location import LocationDataset from .MGBWords import MGBWordsDataset @@ -36,10 +36,10 @@ from .QADI import QADIDataset from .SemEval23T3Propaganda import SemEval23T3PropagandaDataset from .Spam import SpamDataset -from .StanceKhouja20 import StanceKhouja20Dataset -from .StanceUnifiedFC import StanceUnifiedFCDataset -from .STSArSemEval17Track1 import STSArSemEval17Track1Dataset -from .STSArSemEval17Track2 import STSArSemEval17Track2Dataset +from .Khouja20Stance import Khouja20StanceDataset +from .UnifiedFCStance import UnifiedFCStanceDataset +from .SemEval17T1STS import SemEval17T1STSDataset +from .SemEval17T2STS import SemEval17T2STSDataset from .STSQ2Q import Q2QSimDataset from .TyDiQA import TyDiQADataset from .WANLP22T3Propaganda import WANLP22T3PropagandaDataset diff --git a/llmebench/tasks/FactualityKhouja20.py b/llmebench/tasks/FactualityKhouja20.py index 079d2c68..a0745d53 100644 --- a/llmebench/tasks/FactualityKhouja20.py +++ b/llmebench/tasks/FactualityKhouja20.py @@ -3,9 +3,9 @@ from llmebench.tasks.task_base import TaskBase -class FactualityKhouja20Task(TaskBase): +class Khouja20FactualityTask(TaskBase): def __init__(self, **kwargs): - super(FactualityKhouja20Task, self).__init__(**kwargs) + super(Khouja20FactualityTask, self).__init__(**kwargs) def evaluate(self, true_labels, predicted_labels): predicted_labels = [ diff --git a/llmebench/tasks/FactualityUnifiedFC.py b/llmebench/tasks/FactualityUnifiedFC.py index d87c8fd4..7c03503a 100644 --- a/llmebench/tasks/FactualityUnifiedFC.py +++ b/llmebench/tasks/FactualityUnifiedFC.py @@ -3,9 +3,9 @@ from llmebench.tasks.task_base import TaskBase -class FactualityUnifiedFCTask(TaskBase): +class UnifiedFCFactualityTask(TaskBase): def __init__(self, **kwargs): - super(FactualityUnifiedFCTask, self).__init__(**kwargs) + super(UnifiedFCFactualityTask, self).__init__(**kwargs) def evaluate(self, gold_labels, pred_labels): pred_labels = [ diff --git a/llmebench/tasks/StanceKhouja20.py b/llmebench/tasks/StanceKhouja20.py index bbb5930c..93cc207f 100644 --- a/llmebench/tasks/StanceKhouja20.py +++ b/llmebench/tasks/StanceKhouja20.py @@ -3,9 +3,9 @@ from llmebench.tasks.task_base import TaskBase -class StanceKhouja20Task(TaskBase): +class Khouja20StanceTask(TaskBase): def __init__(self, **kwargs): - super(StanceKhouja20Task, self).__init__(**kwargs) + super(Khouja20StanceTask, self).__init__(**kwargs) def evaluate(self, true_labels, predicted_labels): predicted_labels = [ diff --git a/llmebench/tasks/StanceUnifiedFC.py b/llmebench/tasks/StanceUnifiedFC.py index 5ab04762..84377d4f 100644 --- a/llmebench/tasks/StanceUnifiedFC.py +++ b/llmebench/tasks/StanceUnifiedFC.py @@ -3,9 +3,9 @@ from llmebench.tasks.task_base import TaskBase -class StanceUnifiedFCTask(TaskBase): +class UnifiedFCStanceTask(TaskBase): def __init__(self, **kwargs): - super(StanceUnifiedFCTask, self).__init__(**kwargs) + super(UnifiedFCStanceTask, self).__init__(**kwargs) def evaluate(self, true_labels, predicted_labels): predicted_labels = [ diff --git a/llmebench/tasks/__init__.py b/llmebench/tasks/__init__.py index 213952db..4173e185 100644 --- a/llmebench/tasks/__init__.py +++ b/llmebench/tasks/__init__.py @@ -12,8 +12,8 @@ from .DialectID import DialectIDTask from .Emotion import EmotionTask from .FactualityCOVID19 import FactualityCOVID19Task -from .FactualityKhouja20 import FactualityKhouja20Task -from .FactualityUnifiedFC import FactualityUnifiedFCTask +from .FactualityKhouja20 import Khouja20FactualityTask +from .FactualityUnifiedFC import UnifiedFCFactualityTask from .HarmfulDetection import HarmfulDetectionTask from .HateSpeech import HateSpeechTask from .Lemmatization import LemmatizationTask @@ -30,8 +30,8 @@ from .Sarcasm import SarcasmTask from .Sentiment import SentimentTask from .Spam import SpamTask -from .StanceKhouja20 import StanceKhouja20Task -from .StanceUnifiedFC import StanceUnifiedFCTask +from .StanceKhouja20 import Khouja20StanceTask +from .StanceUnifiedFC import UnifiedFCStanceTask from .STSTrack1 import STSTrack1Task from .STSTrack2 import STSTrack2Task from .Subjectivity import SubjectivityTask