deploy at 2025-12-29 10:11:47.435885

Dependency length.ipynb

@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 2,
    "id": "c49f475d-547f-49d8-8550-2f1ad1555a14",
    "metadata": {},
    "outputs": [],
@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 3,
    "id": "cefdbf22-b747-4bea-b279-c9b01e75ff2e",
    "metadata": {},
    "outputs": [],
@@ -94,7 +94,10 @@
     "                    child.dep_ = \"mod\"\n",
     "    for token in doc:\n",
     "        if any(t.text in [\";\", \":\"] for t in doc \n",
-    "               if (token.i < t.i < token.head.i or token.head.i < t.i < token.i) and token.pos_ != \"PUNCT\"):\n",
+    "               if ((token.i < t.i < token.head.i and not\n",
+    "                    (any(p.text == \"(\" for p in doc if token.i < p.i < t.i) and\n",
+    "                     any(p.text == \")\" for p in doc if t.i < p.i < token.head.i))) or \n",
+    "                   token.head.i < t.i < token.i) and token.pos_ != \"PUNCT\"):\n",
     "            token.head = token\n",
     "            token.dep_ = \"root\"\n",
     "        if token.pos_ in [\"VERB\", \"AUX\"]:\n",
@@ -113,7 +116,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 4,
    "id": "23efda66-9d58-4169-9fa0-05de47267b5a",
    "metadata": {},
    "outputs": [],
@@ -165,14 +168,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 6,
    "id": "ba90ff19-c665-49d8-8ad4-5caee885901d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/html": [
-       "<span class=\"tex2jax_ignore\"><svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"f58be662a3bb49738b1eec7a743254f7-0\" class=\"displacy\" width=\"1450\" height=\"399.5\" direction=\"ltr\" style=\"max-width: none; height: 399.5px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
+       "<span class=\"tex2jax_ignore\"><svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"7cae4e9aeafb4cf4bd557e4780eb30b6-0\" class=\"displacy\" width=\"1450\" height=\"399.5\" direction=\"ltr\" style=\"max-width: none; height: 399.5px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
        "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"309.5\">\n",
        "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">They</tspan>\n",
        "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">PRON</tspan>\n",
@@ -214,57 +217,57 @@
        "</text>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-0\" stroke-width=\"2px\" d=\"M70,264.5 C70,177.0 215.0,177.0 215.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-0\" stroke-width=\"2px\" d=\"M70,264.5 C70,177.0 215.0,177.0 215.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M70,266.5 L62,254.5 78,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-1\" stroke-width=\"2px\" d=\"M420,264.5 C420,177.0 565.0,177.0 565.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-1\" stroke-width=\"2px\" d=\"M420,264.5 C420,177.0 565.0,177.0 565.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M420,266.5 L412,254.5 428,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-2\" stroke-width=\"2px\" d=\"M245,264.5 C245,89.5 570.0,89.5 570.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-2\" stroke-width=\"2px\" d=\"M245,264.5 C245,89.5 570.0,89.5 570.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M570.0,266.5 L578.0,254.5 562.0,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-3\" stroke-width=\"2px\" d=\"M245,264.5 C245,2.0 750.0,2.0 750.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-3\" stroke-width=\"2px\" d=\"M245,264.5 C245,2.0 750.0,2.0 750.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M750.0,266.5 L758.0,254.5 742.0,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-4\" stroke-width=\"2px\" d=\"M945,264.5 C945,89.5 1270.0,89.5 1270.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-4\" stroke-width=\"2px\" d=\"M945,264.5 C945,89.5 1270.0,89.5 1270.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M945,266.5 L937,254.5 953,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-5\" stroke-width=\"2px\" d=\"M1120,264.5 C1120,177.0 1265.0,177.0 1265.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-5\" stroke-width=\"2px\" d=\"M1120,264.5 C1120,177.0 1265.0,177.0 1265.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M1120,266.5 L1112,254.5 1128,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
        "\n",
        "<g class=\"displacy-arrow\">\n",
-       "    <path class=\"displacy-arc\" id=\"arrow-f58be662a3bb49738b1eec7a743254f7-0-6\" stroke-width=\"2px\" d=\"M770,264.5 C770,2.0 1275.0,2.0 1275.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-6\" stroke-width=\"2px\" d=\"M770,264.5 C770,2.0 1275.0,2.0 1275.0,264.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
        "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
-       "        <textPath xlink:href=\"#arrow-f58be662a3bb49738b1eec7a743254f7-0-6\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "        <textPath xlink:href=\"#arrow-7cae4e9aeafb4cf4bd557e4780eb30b6-0-6\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
        "    </text>\n",
        "    <path class=\"displacy-arrowhead\" d=\"M1275.0,266.5 L1283.0,254.5 1267.0,254.5\" fill=\"currentColor\"/>\n",
        "</g>\n",
@@ -293,11 +296,7 @@
     {
      "data": {
       "text/plain": [
-       "[(to assume, 0),\n",
-       " (, among the powers of the earth, the separate and equal, 12),\n",
-       " (station to which the laws, 0),\n",
-       " (of nature and, 3),\n",
-       " (of nature’s God entitle them, 0)]"
+       "[(They designated the building, as a national landmark., 0)]"
       ]
      },
      "execution_count": 7,

main.py

@@ -64,7 +64,12 @@ def ssudify(doc):
                     child.dep_ = "mod"
     for token in doc:
         if any(t.text in [";", ":"] for t in doc 
-               if (token.i < t.i < token.head.i or token.head.i < t.i < token.i) and token.pos_ != "PUNCT"):
+               if ((token.i < t.i < token.head.i and not
+                    (any(p.text == "(" for p in doc if token.i < p.i < t.i) and
+                     any(p.text == ")" for p in doc if t.i < p.i < token.head.i))) or 
+                   (token.head.i < t.i < token.i and not
+                    (any(p.text == "(" for p in doc if token.head.i < p.i < t.i) and
+                     any(p.text == ")" for p in doc if t.i < p.i < token.i)))) and token.pos_ != "PUNCT"):
             token.head = token
             token.dep_ = "root"
         if token.pos_ in ["VERB", "AUX"]: