Update app.py

app.py

@@ -6,7 +6,7 @@ from inseq import FeatureAttributionOutput
 st.set_page_config(layout="wide")
 
 dataset = load_dataset("GroNLP/divemt")
-attribution_path = "https://huggingface.co/datasets/inseq/divemt_attributions/resolve/main/divemt-attributions/it/{idx}_{lang}_gradl2_{setting}_{sentence_type}.json.gz"
+attribution_path = "https://huggingface.co/datasets/inseq/divemt_attributions/resolve/main/divemt-attributions/{lang}/{idx}_{lang}_gradl2_{setting}_{sentence_type}.json.gz"
 df = dataset["train"].to_pandas()
 unique_src = df[["item_id", "src_text"]].drop_duplicates(subset="item_id")
 langs = list(df["lang_id"].unique())
@@ -19,6 +19,15 @@ st.markdown("""
 ##### Inside every generated language section, you will find the translations for all the available settings, alongside aligned edits and a collection of collected metadata. You can filter the shown settings to see the aligned edits annotations.
 """)
 
+divemt_to_spacy_lang_map = {
+    "ara": "ar",
+    "nld": "nl",
+    "ita": "it",
+    "tur": "tr",
+    "ukr": "uk",
+    "vie": "vi",
+}
+
 with st.expander("Explore examples"):
     col1, col2, _ = st.columns([3,2,5])
     with col1:
@@ -94,7 +103,7 @@ for lang in langs:
                 st.markdown(f"<b>Attributions</b>:", unsafe_allow_html=True)
                 st.text("Click on checkboxes to show/hide the respective attributions computed with mBART 1-to-50.")
                 for sentence_type in ["mt", "pe", "diff"]:
-                    url = attribution_path.format(idx=item_id, setting=setting, sentence_type=sentence_type, lang=lang)
+                    url = attribution_path.format(idx=item_id, setting=setting, sentence_type=sentence_type, lang=divemt_to_spacy_lang_map[lang])
                     try:
                         g = urllib.request.urlopen(url)
                         fpath = f"attr_{lang}_{sentence_type}.json.gz"