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}_it_gradl2_{setting}_{sentence_type}.json.gz"
+attribution_path = "https://huggingface.co/datasets/inseq/divemt_attributions/resolve/main/divemt-attributions/it/{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())
@@ -80,9 +80,9 @@ for lang in langs:
             st.markdown(f"<b>Aligned edits</b>:", unsafe_allow_html=True)
             if dic["aligned_edit"] is not None:
                 aligned_edit = dic["aligned_edit"]
-                if lang == 'ara' and len(dic["aligned_edit"].split("EVAL: ")) == 2:
-                    edits_reverse = aligned_edit.split("EVAL: ")[1][::-1]
-                    aligned_edit = aligned_edit.split("EVAL: ")[0] + "EVAL: " + edits_reverse
+                #if lang == 'ara' and len(dic["aligned_edit"].split("EVAL: ")) == 2:
+                #    edits_reverse = aligned_edit.split("EVAL: ")[1][::-1]
+                #    aligned_edit = aligned_edit.split("EVAL: ")[0] + "EVAL: " + edits_reverse
                 aligned_edit = aligned_edit.replace("\\n", "\n").replace("REF:", "MT :").replace("HYP:", "PE :")
                 st.text(aligned_edit)
             else:
@@ -94,10 +94,10 @@ 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)
+                    url = attribution_path.format(idx=item_id, setting=setting, sentence_type=sentence_type, lang=lang)
                     try:
                         g = urllib.request.urlopen(url)
-                        fpath = f"attr_{sentence_type}.json.gz"
+                        fpath = f"attr_{lang}_{sentence_type}.json.gz"
                         with open(fpath, 'b+w') as f:
                             f.write(g.read())
                         attr = FeatureAttributionOutput.load(fpath, decompress=True)