Update src/tasks_content.py

src/tasks_content.py

@@ -11,6 +11,30 @@ TASKS_PRETTY = {
 TASKS_PRETTY_REVERSE = {value: key for key, value in TASKS_PRETTY.items()}
 
 TASKS_DESCRIPTIONS = {
+    "library_based_code_generation": "cool description for Library Usage Examples Generation task",
+
+    "ci_builds_repair": "cool description for Bug Localization on Build Logs task",
+
+    "project_code_completion": """# Project-Level Code Completion\n
+        
+        Our Project-Level Code Completion 🤗 [JetBrains-Research/lca-code-completion](https://huggingface.co/datasets/JetBrains-Research/lca-code-completion) includes four datasets:
+        * `small-context`: 144 data points,
+        * `medium-context`: 224 data points,
+        * `large-context`: 270 data points,
+        * `huge-context`: 296 data points.
+
+        We use standard Exact Match (EM) metric for one-line code completion.
+        We evaluate Exact Match for different line categories:
+        * *infile* – functions and classes are from the completion file;
+        * *inproject* – functions and files are from the repository snapshot;
+        * *committed* – functions and classes are from the files that were added on the completion file commit;
+        * *common* – functions and classes with common names, e.g., `main`, `get`, etc.;
+        * *non-informative* – short/long lines, import/print lines, or comment lines;
+        * *random* – lines that doesn't fit to any of previous categories.
+
+        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `code_completion` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
+        """,
+    
     "commit_message_generation": """# Commit Message Generation\n
         
         Our Commit Message Generation benchmark 🤗 [JetBrains-Research/lca-commit-message-generation](https://huggingface.co/datasets/JetBrains-Research/lca-commit-message-generation) includes 163 manually curated commits from Python projects.  
@@ -25,6 +49,7 @@ TASKS_DESCRIPTIONS = {
         
         **Note.** The leaderboard is sorted by ROUGE-1 metric by default.       
         """,
+    
     "bug_localization": """# Bug Localization\n
         
         Our Module-to-Text benchmark 🤗 [JetBrains-Research/lca-bug-localization](https://huggingface.co/datasets/JetBrains-Research/lca-bug-localization) includes 7,479 bug issue descriptions with information about pull request that fix them for Python, Java and Kotlin projects. 
@@ -32,6 +57,7 @@ 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_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. 
 
@@ -40,30 +66,6 @@ TASKS_DESCRIPTIONS = {
 
         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).
         """,
-    
-    "library_usage": "cool description for Library Usage Examples Generation task",
-    
-    "project_code_completion": """# Project-Level Code Completion\n
-        
-        Our Project-Level Code Completion 🤗 [JetBrains-Research/lca-code-completion](https://huggingface.co/datasets/JetBrains-Research/lca-code-completion) includes four datasets:
-        * `small-context`: 144 data points,
-        * `medium-context`: 224 data points,
-        * `large-context`: 270 data points,
-        * `huge-context`: 296 data points.
-
-        We use standard Exact Match (EM) metric for one-line code completion.
-        We evaluate Exact Match for different line categories:
-        * *infile* – functions and classes are from the completion file;
-        * *inproject* – functions and files are from the repository snapshot;
-        * *committed* – functions and classes are from the files that were added on the completion file commit;
-        * *common* – functions and classes with common names, e.g., `main`, `get`, etc.;
-        * *non-informative* – short/long lines, import/print lines, or comment lines;
-        * *random* – lines that doesn't fit to any of previous categories.
-
-        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `code_completion` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
-        """,
-    
-    "bug_localization_build_logs": "cool description for Bug Localization on Build Logs task",
 }