Fix error / Beautify m2t

src/leaderboard_formatting.py

@@ -70,7 +70,6 @@ def get_columns_per_task(task_id: str) -> List[str]:
         return ["Model Name", "Context Size", "Dataset Name", "Dataset"] + metrics_per_task + ["Availability", "Submitted By", "Resources"]
     if task_id == 'bug_localization':
         return ["Model Name", "Availability", "Context Size", "Dataset"] + metrics_per_task + ["Submitted By", "Resources"]
-    if task_id == 'bug_localization':
     return ["Model Name", "Context Size", "Availability"] + metrics_per_task + ["Submitted By", "Resources"]
 
 

src/tasks_content.py

@@ -3,7 +3,7 @@ from typing import Optional
 TASKS_PRETTY = {
     "commit_message_generation": "Commit Message Generation",
     "bug_localization": "Bug Localization on Issue",
-    "module_to_text": "Module-to-Text",
+    "module_summarization": "Module Summarization",
     "library_usage": "Library Usage Examples Generation",
     "project_code_completion": "Project-level Code Completion",
     "bug_localization_build_logs": "Bug Localization on Build Logs",
@@ -32,15 +32,11 @@ TASKS_DESCRIPTIONS = {
         Moreover, 150 data points from the test split were manually verified and can be used for bug localization approaches evaluation.
         We used information retrieval metrics such as R@k, P@k and F1-score for evaluation, taking k equals to 2.
     """,
-    "module_to_text": """# Module-to-Text\n
+    "module_summarization": """# Module Summarization\n
+        Our Module-to-Text benchmark 🤗 [JetBrains-Research/lca-module-summarization](https://huggingface.co/datasets/JetBrains-Research/lca-module-summarization) includes 216 manually curated text files describing different documentation of opensource permissive Python projects. 
 
-        Our Module-to-Text benchmark 🤗 [JetBrains-Research/lca-module-to-text](https://huggingface.co/datasets/JetBrains-Research/lca-module-to-text) includes 206 manually curated text files describing modules from different Python projects.
-
-        We use the following metrics for evaluation:
-        * [ChrF](https://huggingface.co/spaces/evaluate-metric/chrf)
-        * [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge)
-        * [BERTScore](https://huggingface.co/spaces/evaluate-metric/bertscore)
-        * ChatGPT-Turing-Test
+        We use new metric for evaluation:
+        * [CompScore](https://github.com/JetBrains-Research/lca-baselines/tree/module2text)
 
         For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `module2text` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
         """,
@@ -58,5 +54,8 @@ def get_submission_text_files_for_task(task_pretty: Optional[str]) -> str:
 
     if task_id == "commit_message_generation":
         return f"""**{task_pretty} Instructions:**\n\n* Please, attach files in [JSONLines format](https://jsonlines.org/). For an example, check the predictions provided by 🏟️ Long Code Arena Team in  🤗 [JetBrains-Research/lca-results](https://huggingface.co/datasets/JetBrains-Research/lca-results/tree/main/commit_message_generation/predictions). Make sure to include `"prediction"` and `"reference"` fields for each example, the rest are optional."""
+    
+    if task_id == "module_summarization":
+        return f"""**{task_pretty} Instructions:**\n\n* Please, attach files in [JSONLines format](https://jsonlines.org/). For an example, check the predictions provided by 🏟️ Long Code Arena Team in  🤗 [JetBrains-Research/lca-results](https://huggingface.co/datasets/JetBrains-Research/lca-results/tree/main/commit_message_generation/predictions). Make sure to include `"prediction"` and `"reference"` fields for each example, the rest are optional."""
 
     return f"**{task_pretty} Instructions:**\n\n* 🚧 There are no instructions for the current task yet."