added structured annotation section

datacards/curation.py

@@ -12,7 +12,7 @@ from .streamlit_utils import (
 
 N_FIELDS_ORIGINAL = 4
 N_FIELDS_LANGUAGE = 12
-N_FIELDS_ANNOTATIONS = 0
+N_FIELDS_ANNOTATIONS = 10
 N_FIELDS_CONSENT = 0
 N_FIELDS_PII = 0
 N_FIELDS_MAINTENANCE = 0
@@ -148,11 +148,81 @@ def curation_page():
             key_list=key_pref + ["filtered-criteria"],
             help="Describe the process for selecting instances to include in the dataset, including any tools used. If no selection was done, enter N/A.",
         )
+
     with st.expander("Structured Annotations", expanded=False):
         key_pref = ["curation", "annotations"]
         st.session_state.card_dict["curation"][
             "annotations"
         ] = st.session_state.card_dict["curation"].get("annotations", {})
+
+        make_radio(
+            label="Does the dataset have additional annotations for each instance?",
+            options=["none", "found", "automatically created", "expert created", "crowd-sourced"],
+            key_list=key_pref + ["origin"],
+            help="Was any additional data collected?",
+        )
+
+        # TODO: If yes....
+        # If expert or crowdsourced, this branch
+        make_radio(
+            label="What is the number of raters ",
+            options=["unknown", "1", "2<n<10", "11<n<50", "51<n<100", "n>100"],
+            key_list=key_pref + ["rater-number"],
+            help="How many raters were used to create the additional annotations?",
+        )
+        make_text_area(
+            label="Describe the qualifications required of an annotator.",
+            key_list=key_pref + ["rater-qualifications"],
+            help="e.g., languages or dialects they speak, education requirements, number of HITs (if MTurk).",
+        )
+        make_radio(
+            label="How many annotators saw each training example?",
+            options=["0", "1", "2", "3", "4", "5", ">5"],
+            key_list=key_pref + ["rater-training-num"],
+            help="",
+        )
+        make_radio(
+            label="How many annotators saw each test example?",
+            options=["0", "1", "2", "3", "4", "5", ">5"],
+            key_list=key_pref + ["rater-test-num"],
+            help="",
+        )
+        make_radio(
+            label="Was an annotation service used?",
+            options=["yes", "no", "unknown"],
+            key_list=key_pref + ["rater-annotation-service-bool"],
+            help="",
+        )
+        # TODO if yes
+        make_multiselect(
+            label="Which annotation services were used?",
+            options=[
+                "Amazon Mechanical Turk", "Prolific Academic",
+                "Upwork", "Appen", "Crowdflower", "other"
+            ],
+            key_list=key_pref + ["rater-annotation-service"],
+        )
+
+
+        make_text_area(
+            label="Purpose and values for each annoation",
+            key_list=key_pref + ["values"],
+            help="Describe the purpose and possible values for each kind of annotation.",
+        )
+        make_multiselect(
+            label="Quality control measures?",
+            options=["none", "unknown",  "validated by another rater", "validated by data curators", "validated through automated script", "other"],
+            key_list=key_pref + ["quality-control"],
+            help="How was annotation quality controlled for / what control measures were put in place to ensure annotation quality?",
+        )
+        # TODO: If not none / unknown
+        make_text_area(
+            label="Describe the quality control measures that were taken.",
+            key_list=key_pref + ["quality-control-details"],
+            help="Describe how quality was ensured in the data curation process.",
+        )
+
+
     with st.expander("Consent", expanded=False):
         key_pref = ["curation", "consent"]
         st.session_state.card_dict["curation"]["consent"] = st.session_state.card_dict[