fix L-MT on default page

app.py

@@ -156,8 +156,17 @@ with demo:
             with gr.Row():
                 tasks_checkbox = gr.CheckboxGroup(
                     label="Select Tasks",
-                    choices=["L-NER", "RR", "CJPE", "BAIL", "LSI", "PCR", "SUMM"],
-                    value=["L-NER", "RR", "CJPE", "BAIL", "LSI", "PCR", "SUMM"],
+                    choices=[
+                        "L-NER",
+                        "RR",
+                        "CJPE",
+                        "BAIL",
+                        "LSI",
+                        "PCR",
+                        "SUMM",
+                        "L-MT",
+                    ],
+                    value=["L-NER", "RR", "CJPE", "BAIL", "LSI", "PCR", "SUMM", "L-MT"],
                     interactive=True,
                 )
 
@@ -231,7 +240,7 @@ with demo:
             leaderboard_table = gr.components.Dataframe(
                 value=load_data(
                     # "baseline",
-                    ["L-NER", "RR", "CJPE", "BAIL", "LSI", "PCR", "SUMM"],
+                    ["L-NER", "RR", "CJPE", "BAIL", "LSI", "PCR", "SUMM", "L-MT"],
                     task_metrics=task_metrics,
                 ),
                 interactive=True,
@@ -392,10 +401,13 @@ with demo:
                 outputs=leaderboard_table,
             )
 
-    with gr.Accordion("Submit the results of your Method"):
+    with gr.Accordion("Submit the Results of your Method"):
         with gr.Row():
             with gr.Column():
-                method_name_textbox = gr.Textbox(label="Method")
+                method_name_textbox = gr.Textbox(
+                    label="Method",
+                )
+                submitted_by_textbox = gr.Textbox(label="Submitted By (Team Name)")
                 url_textbox = gr.Textbox(label="Github Link")
                 organisation = gr.Textbox(label="Organisation")
                 mail = gr.Textbox(label="Contact email")
@@ -407,6 +419,7 @@ with demo:
             add_new_eval,
             [
                 method_name_textbox,
+                submitted_by_textbox,
                 url_textbox,
                 file_output,
                 organisation,

submissions/baseline/results.json

@@ -1 +1 @@
-[{"Method": "SOTA", "Submitted By": "multiple", "Github Link": "exploration-lab.github.io/IL-TUR/", "L-NER": {"strict mF1": "48.58"}, "RR": {"mF1": "69.01"}, "CJPE": {"mF1": "81.31", "ROUGE-L": "56.00", "BLEU": "32.00"}, "BAIL": {"mF1": "81"}, "LSI": {"mF1": "28.08"}, "PCR": {"muF1@K": "39.15"}, "SUMM": {"ROUGE-L": "33.00", "BERTSCORE": "86.00"}, "L-MT": {"BLEU": "28.00", "GLEU": "32.00", "chrF++": "57.00"}}, {"Method": "BERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "39.59"}, "RR": {"mF1": "58"}, "CJPE": {"mF1": "71.14", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "18.44"}, "SUMM": {"ROUGE-L": "9.24", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "LegalBERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "45.58"}, "RR": {"mF1": "54"}, "CJPE": {"mF1": "78.21", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "21.74"}, "SUMM": {"ROUGE-L": "8.67", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "InLegalBERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "48.58"}, "RR": {"mF1": "58"}, "CJPE": {"mF1": "81.31", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "26.23"}, "SUMM": {"ROUGE-L": "7.57", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "GPT-3.5 (0-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "30.59"}, "RR": {"mF1": "30.95"}, "CJPE": {"mF1": "54.17", "ROUGE-L": "30.00", "BLEU": "8.00"}, "BAIL": {"mF1": "51.04"}, "LSI": {"mF1": "21.55"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "21.00", "BERTSCORE": "85.00"}, "L-MT": {"BLEU": "23.00", "GLEU": "28.00", "chrF++": "42.00"}}, {"Method": "GPT-3.5 (1-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "23.68"}, "RR": {"mF1": "30.05"}, "CJPE": {"mF1": "51.46", "ROUGE-L": "29.00", "BLEU": "15.00"}, "BAIL": {"mF1": "46.35"}, "LSI": {"mF1": "22.61"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "20.00", "BERTSCORE": "84.00"}, "L-MT": {"BLEU": "25.00", "GLEU": "28.00", "chrF++": "43.00"}}, {"Method": "GPT-3.5 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "32.84"}, "RR": {"mF1": "30.31"}, "CJPE": {"mF1": "56.74", "ROUGE-L": "30.00", "BLEU": "11.00"}, "BAIL": {"mF1": "61"}, "LSI": {"mF1": "21.4"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "22.00", "BERTSCORE": "84.00"}, "L-MT": {"BLEU": "26.00", "GLEU": "29.00", "chrF++": "43.00"}}, {"Method": "GPT-4 (0-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "13.65"}, "RR": {"mF1": "37.37"}, "CJPE": {"mF1": "68.29", "ROUGE-L": "40.00", "BLEU": "14.00"}, "BAIL": {"mF1": "51.46"}, "LSI": {"mF1": "23.99"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "23.00", "BERTSCORE": "85.00"}, "L-MT": {"BLEU": "33.00", "GLEU": "36.00", "chrF++": "50.00"}}, {"Method": "GPT-4 (1-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "10.51"}, "RR": {"mF1": "37.43"}, "CJPE": {"mF1": "47.26", "ROUGE-L": "39.00", "BLEU": "16.00"}, "BAIL": {"mF1": "56.9"}, "LSI": {"mF1": "22.26"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "16.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "35.00", "GLEU": "38.00", "chrF++": "52.00"}}, {"Method": "GPT-4 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "24.03"}, "RR": {"mF1": "38.18"}, "CJPE": {"mF1": "60.44", "ROUGE-L": "43.00", "BLEU": "18.00"}, "BAIL": {"mF1": "66.67"}, "LSI": {"mF1": "20.53"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "17.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "36.00", "GLEU": "39.00", "chrF++": "53.00"}}, {"Method": "GPT-5 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "dummy submission", "L-NER": {"strict mF1": "24.03"}, "RR": {"mF1": "38.18"}, "CJPE": {"mF1": "60.44", "ROUGE-L": "43.00", "BLEU": "18.00"}, "BAIL": {"mF1": "66.67"}, "LSI": {"mF1": "20.53"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "17.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "36.00", "GLEU": "39.00", "chrF++": "53.00"}}, {"Method": "GPT-5 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "dummy submission", "L-NER": {"strict mF1": "24.03"}, "RR": {"mF1": "38.18"}, "CJPE": {"mF1": "60.44", "ROUGE-L": "43.00", "BLEU": "18.00"}, "BAIL": {"mF1": "66.67"}, "LSI": {"mF1": "20.53"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "17.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "36.00", "GLEU": "39.00", "chrF++": "53.00"}}]
+[{"Method": "SOTA", "Submitted By": "multiple", "Github Link": "exploration-lab.github.io/IL-TUR/", "L-NER": {"strict mF1": "48.58"}, "RR": {"mF1": "69.01"}, "CJPE": {"mF1": "81.31", "ROUGE-L": "56.00", "BLEU": "32.00"}, "BAIL": {"mF1": "81"}, "LSI": {"mF1": "28.08"}, "PCR": {"muF1@K": "39.15"}, "SUMM": {"ROUGE-L": "33.00", "BERTSCORE": "86.00"}, "L-MT": {"BLEU": "28.00", "GLEU": "32.00", "chrF++": "57.00"}}, {"Method": "BERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "39.59"}, "RR": {"mF1": "58"}, "CJPE": {"mF1": "71.14", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "18.44"}, "SUMM": {"ROUGE-L": "9.24", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "LegalBERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "45.58"}, "RR": {"mF1": "54"}, "CJPE": {"mF1": "78.21", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "21.74"}, "SUMM": {"ROUGE-L": "8.67", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "InLegalBERT", "Submitted By": "multiple", "Github Link": "", "L-NER": {"strict mF1": "48.58"}, "RR": {"mF1": "58"}, "CJPE": {"mF1": "81.31", "ROUGE-L": "-", "BLEU": "-"}, "BAIL": {"mF1": "-"}, "LSI": {"mF1": "-"}, "PCR": {"muF1@K": "26.23"}, "SUMM": {"ROUGE-L": "7.57", "BERTSCORE": "-"}, "L-MT": {"BLEU": "-", "GLEU": "-", "chrF++": "-"}}, {"Method": "GPT-3.5 (0-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "30.59"}, "RR": {"mF1": "30.95"}, "CJPE": {"mF1": "54.17", "ROUGE-L": "30.00", "BLEU": "8.00"}, "BAIL": {"mF1": "51.04"}, "LSI": {"mF1": "21.55"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "21.00", "BERTSCORE": "85.00"}, "L-MT": {"BLEU": "23.00", "GLEU": "28.00", "chrF++": "42.00"}}, {"Method": "GPT-3.5 (1-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "23.68"}, "RR": {"mF1": "30.05"}, "CJPE": {"mF1": "51.46", "ROUGE-L": "29.00", "BLEU": "15.00"}, "BAIL": {"mF1": "46.35"}, "LSI": {"mF1": "22.61"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "20.00", "BERTSCORE": "84.00"}, "L-MT": {"BLEU": "25.00", "GLEU": "28.00", "chrF++": "43.00"}}, {"Method": "GPT-3.5 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "32.84"}, "RR": {"mF1": "30.31"}, "CJPE": {"mF1": "56.74", "ROUGE-L": "30.00", "BLEU": "11.00"}, "BAIL": {"mF1": "61"}, "LSI": {"mF1": "21.4"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "22.00", "BERTSCORE": "84.00"}, "L-MT": {"BLEU": "26.00", "GLEU": "29.00", "chrF++": "43.00"}}, {"Method": "GPT-4 (0-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "13.65"}, "RR": {"mF1": "37.37"}, "CJPE": {"mF1": "68.29", "ROUGE-L": "40.00", "BLEU": "14.00"}, "BAIL": {"mF1": "51.46"}, "LSI": {"mF1": "23.99"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "23.00", "BERTSCORE": "85.00"}, "L-MT": {"BLEU": "33.00", "GLEU": "36.00", "chrF++": "50.00"}}, {"Method": "GPT-4 (1-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "10.51"}, "RR": {"mF1": "37.43"}, "CJPE": {"mF1": "47.26", "ROUGE-L": "39.00", "BLEU": "16.00"}, "BAIL": {"mF1": "56.9"}, "LSI": {"mF1": "22.26"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "16.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "35.00", "GLEU": "38.00", "chrF++": "52.00"}}, {"Method": "GPT-4 (2-shot)", "Submitted By": "IL-TUR", "Github Link": "", "L-NER": {"strict mF1": "24.03"}, "RR": {"mF1": "38.18"}, "CJPE": {"mF1": "60.44", "ROUGE-L": "43.00", "BLEU": "18.00"}, "BAIL": {"mF1": "66.67"}, "LSI": {"mF1": "20.53"}, "PCR": {"muF1@K": "-"}, "SUMM": {"ROUGE-L": "17.00", "BERTSCORE": "81.00"}, "L-MT": {"BLEU": "36.00", "GLEU": "39.00", "chrF++": "53.00"}}]

uploads.py

@@ -4,6 +4,7 @@ import os
 import datetime
 import json
 import pandas as pd
+import gradio as gr
 
 LEADERBOARD_PATH = "Exploration-Lab/IL-TUR-Leaderboard"
 # RESULTS_PATH = "Exploration-Lab/IL-TUR-Leaderboard-results"
@@ -42,11 +43,20 @@ def input_verification(method_name, url, path_to_file, organisation, mail):
     if path_to_file is None:
         return format_warning("Please attach a file.")
 
+    # check the required fields
+    required_fields = ["Method", "Submitted By", "url", "organisation", "mail"]
+
+    # Check if the required_fields are not blank
+    for field in required_fields:
+        if field not in locals():
+            raise gr.Error(f"{field} cannot be blank")
+
     return parsed_mail
 
 
 def add_new_eval(
     method_name: str,
+    submitted_by: str,
     url: str,
     path_to_file: str,
     organisation: str,