Upload 2 files

app.py

@@ -38,7 +38,6 @@ UI = {
     "fo": {"w":"Orð", "t":"Mark", "s":"Útgreining", "m":"Útgreinað marking"},
     "en": {"w":"Word","t":"Tag", "s":"Analysis", "m":"Expanded tags"},
 }
-
 MODEL_LINK = "https://huggingface.co/Setur/BRAGD"
 
 # Theme color: #89AFA9 (+ close shades) + system font
@@ -50,11 +49,14 @@ CSS = """
 body, .gradio-container, .prose, .markdown, textarea, input, select, button, table{
   font-family:-apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Arial, "Noto Sans", sans-serif !important;
 }
+
+/* Buttons */
 .gr-button-primary, button.primary, .primary{
   background:var(--primary-500)!important; border-color:var(--primary-600)!important; color:#0b1b19!important;
 }
 .gr-button-primary:hover, button.primary:hover, .primary:hover{ background:var(--primary-600)!important; }
 a{ color:var(--primary-700)!important; }
+.gr-button-primary{ padding: 0.32rem 0.75rem !important; font-size: 0.95rem !important; }
 
 /* Dataframe column wrapping: keep Orð + Mark on one line */
 .gr-dataframe table td:nth-child(1),
@@ -65,20 +67,18 @@ a{ color:var(--primary-700)!important; }
 .gr-dataframe table td:nth-child(2),
 .gr-dataframe table th:nth-child(2){
   white-space: nowrap !important;
-  width: 18% !important;
+  width: 20% !important;
   font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace !important;
 }
 .gr-dataframe table td:nth-child(3),
 .gr-dataframe table th:nth-child(3){
   white-space: normal !important;
-  width: 64% !important;
+  width: 62% !important;
 }
 
-/* Make the language dropdown compact */
-#lang_dd { max-width: 170px; }
-
-/* Slightly smaller primary button */
-.gr-button-primary{ padding: 0.35rem 0.85rem !important; font-size: 0.95rem !important; }
+/* Compact dropdown on the right (avoid huge grey container) */
+#lang_dd { max-width: 150px; min-width: 150px; margin-left: auto; }
+#lang_dd > div { width: 150px !important; }
 """
 
 # ----------------------------
@@ -238,6 +238,7 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
     Útgreining / Analysis:
     - plain words (no letters/hyphens)
     - pronouns: start at subcategory, not word class
+    - conjunctions: subcategory already includes 'sambindingarorð' in label
     - DGd: show only fyriseting/preposition
     - supine: show only supine + voice (drop verb/number/tense/person etc.)
     """
@@ -258,7 +259,7 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
 
     parts = []
 
-    # Pronouns + conjunctions: subcategory already carries the head noun (fornavn / sambindingarorð)
+    # Pronouns + conjunctions: start at subcategory (the label already contains the head)
     if wc in {"P","C"}:
         subc = group_code(vec, "subcategory")
         subl = clean_label(label_for(lang, "subcategory", wc, subc) or "")
@@ -289,10 +290,7 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
     return ", ".join(parts)
 
 def expanded_text(vec: torch.Tensor, lang: str) -> str:
-    """
-    Útgreinað marking / Expanded tags:
-    codes + labels (useful for debugging and linguists)
-    """
+    """Útgreinað marking / Expanded tags: codes + labels."""
     lang = "fo" if lang=="fo" else "en"
     wc = wc_code(vec)
     parts = []
@@ -335,11 +333,9 @@ def compute_codes_by_wc():
 CODES_BY_WC = compute_codes_by_wc()
 
 def build_overview(lang: str) -> str:
-    """
-    Overview under each word class with the letter codes actually used in the CURRENT CSV.
-    """
+    """Markayvirlit / Tag Overview under each word class (codes used in current CSV)."""
     lang = "fo" if lang=="fo" else "en"
-    title = "### Markingaryvirlit" if lang=="fo" else "### Tag Overview"
+    title = "### Markayvirlit" if lang=="fo" else "### Tag Overview"
     lines = [title, ""]
 
     for wc in sorted(CODES_BY_WC.keys()):
@@ -350,6 +346,7 @@ def build_overview(lang: str) -> str:
             cs = sorted(CODES_BY_WC[wc].get(g, set()))
             if not cs:
                 continue
+
             group_name = {
                 "fo": {
                     "subcategory":"Undirflokkur", "gender":"Kyn", "number":"Tal", "case":"Fall",
@@ -458,36 +455,38 @@ def render(rows_state, lang: str):
 # ----------------------------
 theme = gr.themes.Soft()
 
-with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
-    # Compact header: info left, input right
+with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
+    # New layout: textbox left, info right (button under info)
     with gr.Row(equal_height=True):
-        with gr.Column(scale=1, min_width=280):
-            gr.Markdown(
-                "### BRAGD-markarin\n"
-                "Skriv ein setning og fá hann markaðan.\n\n"
-                f"**Myndil / Model:** [{MODEL_ID}]({MODEL_LINK})"
-            )
         with gr.Column(scale=2):
             inp = gr.Textbox(
-                lines=5,
+                lines=6,
                 placeholder="Skriva her ... / Type here ...",
                 show_label=False,
             )
+        with gr.Column(scale=1, min_width=280):
+            gr.Markdown(
+                "### Marka\n"
+                "Skriv setningin í kassan vinstrumegin og fá hann markaðan.\n\n"
+                f"**Myndil / Model:** [{MODEL_ID}]({MODEL_LINK})"
+            )
             btn = gr.Button("Marka / Tag", variant="primary")
 
     state = gr.State([])
 
     # Results header row (components hide until first run)
     with gr.Row():
-        results_title = gr.Markdown("### Úrslit / Results", visible=False)
-        lang = gr.Dropdown(
-            choices=[("Føroyskt","fo"), ("English","en")],
-            value="fo",
-            show_label=False,
-            filterable=False,
-            elem_id="lang_dd",
-            visible=False,
-        )
+        with gr.Column(scale=5):
+            results_title = gr.Markdown("### Úrslit / Results", visible=False)
+        with gr.Column(scale=1, min_width=170):
+            lang = gr.Dropdown(
+                choices=[("Føroyskt","fo"), ("English","en")],
+                value="fo",
+                show_label=False,
+                filterable=False,
+                elem_id="lang_dd",
+                visible=False,
+            )
 
     out_df = gr.Dataframe(
         value=pd.DataFrame(columns=[UI["fo"]["w"], UI["fo"]["t"], UI["fo"]["s"]]),
@@ -499,7 +498,8 @@ with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
         visible=False,
     )
 
-    with gr.Accordion("Útgreinað marking / Expanded tags", open=False):
+    # Hide Expanded tags accordion until tagged
+    with gr.Accordion("Útgreinað marking / Expanded tags", open=False, visible=False) as expanded_acc:
         out_mean_df = gr.Dataframe(
             value=pd.DataFrame(columns=[UI["fo"]["w"], UI["fo"]["t"], UI["fo"]["m"]]),
             wrap=True,
@@ -507,16 +507,15 @@ with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
             show_label=False,
             row_count=(0, "fixed"),
             col_count=(3, "fixed"),
-            visible=False,
+            visible=True,
         )
 
-    with gr.Accordion("Markingaryvirlit / Tag Overview", open=False):
+    with gr.Accordion("Markayvirlit / Tag Overview", open=False):
         overview_md = gr.Markdown("", visible=False)
 
     def on_tag(sentence, lang_choice):
         rows = run_model(sentence)
         df_main, df_mean, overview = render(rows, lang_choice)
-
         return (
             rows,
             gr.update(value=df_main, visible=True),
@@ -524,6 +523,7 @@ with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
             gr.update(value=overview, visible=True),
             gr.update(visible=True),   # results_title
             gr.update(visible=True),   # lang
+            gr.update(visible=True),   # expanded_acc
         )
 
     def on_lang(rows, lang_choice):
@@ -537,7 +537,7 @@ with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
     btn.click(
         on_tag,
         inputs=[inp, lang],
-        outputs=[state, out_df, out_mean_df, overview_md, results_title, lang],
+        outputs=[state, out_df, out_mean_df, overview_md, results_title, lang, expanded_acc],
         queue=False,
     )
 

tag_labels.json

@@ -84,7 +84,7 @@
           "G": "genitive"
         },
         "article": {
-          "A": "with suffixed definite article"
+          "A": "definite"
         },
         "proper": {
           "P": "Proper Noun"
@@ -125,8 +125,8 @@
           "A": "absolute superlative"
         },
         "declension": {
-          "S": "strong",
-          "W": "weak",
+          "S": "strong declension",
+          "W": "weak declension",
           "e": "no-declension"
         },
         "gender": {
@@ -163,9 +163,9 @@
           "N": "neuter"
         },
         "person": {
-          "1": "1st pers",
-          "2": "2nd pers",
-          "3": "3rd pers"
+          "1": "1st person",
+          "2": "2nd person",
+          "3": "3rd person"
         },
         "number": {
           "S": "singular",
@@ -206,7 +206,7 @@
       },
       "V": {
         "word_class": {
-          "V": "verb (except for participle)"
+          "V": "verb"
         },
         "mood": {
           "I": "infinitive",
@@ -235,15 +235,15 @@
       },
       "L": {
         "word_class": {
-          "L": "participle"
+          "L": "past participle"
         },
         "voice": {
           "A": "active",
           "M": "mediopassive"
         },
         "declension": {
-          "S": "strong",
-          "W": "weak",
+          "S": "strong declension",
+          "W": "weak declension",
           "e": "no-declension"
         },
         "gender": {
@@ -456,8 +456,8 @@
           "A": "absolutt hástig"
         },
         "declension": {
-          "S": "sterk",
-          "W": "veik",
+          "S": "sterk bending",
+          "W": "veik bending",
           "e": "eingin sterk/veik bending"
         },
         "gender": {
@@ -494,9 +494,9 @@
           "N": "hvørkikyn"
         },
         "person": {
-          "1": "fyrsti persónur",
-          "2": "annar persónur",
-          "3": "triði persónur"
+          "1": "1. persónur",
+          "2": "2. persónur",
+          "3": "3. persónur"
         },
         "number": {
           "S": "eintal",
@@ -577,8 +577,8 @@
           "M": "miðalsøgn"
         },
         "declension": {
-          "S": "sterk",
-          "W": "veik",
+          "S": "sterk bending",
+          "W": "veik bending",
           "e": "eingin sterk/veik bending"
         },
         "gender": {