972 lines
414 KiB
Plaintext
972 lines
414 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 116,
|
||
"id": "263af9e9",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import pickle, tensorflow as tf, numpy as np\n",
|
||
"from tensorflow.keras.models import Model\n",
|
||
"from tensorflow.keras.layers import (\n",
|
||
" Input,\n",
|
||
" Embedding,\n",
|
||
" SpatialDropout1D,\n",
|
||
" Bidirectional,\n",
|
||
" LSTM,\n",
|
||
" TimeDistributed,\n",
|
||
" Dense,\n",
|
||
")\n",
|
||
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"from collections import Counter\n",
|
||
"from itertools import zip_longest"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 117,
|
||
"id": "4fc87f1b",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"total kalimat 1639\n",
|
||
"NER Label Count || SRL Label Count \n",
|
||
"-------------------------------------------------------\n",
|
||
"O 7261 || O 4182 \n",
|
||
"B-TIME 189 || ARGM-TMP 1292 \n",
|
||
"B-PER 1313 || ARG0 1965 \n",
|
||
"B-LOC 1554 || V 1738 \n",
|
||
"I-PER 226 || ARG1 1308 \n",
|
||
"B-DATE 339 || ARGM-LOC 1503 \n",
|
||
"I-DATE 647 || ARG2 293 \n",
|
||
"B-ETH 213 || ARGM-MOD 39 \n",
|
||
"I-ETH 217 || ARGM-MNR 37 \n",
|
||
"B-EVENT 70 || ARGM-NEG 6 \n",
|
||
"I-EVENT 55 || ARGM-DIR 41 \n",
|
||
"I-LOC 32 || ARGM-CAU 21 \n",
|
||
"B-MISC 14 || \n",
|
||
"I-MISC 3 || \n",
|
||
"I-TIME 46 || \n",
|
||
"B-ORG 21 || \n",
|
||
"I-ORG 18 || \n",
|
||
"B-QUANT 46 || \n",
|
||
"B-MAT 99 || \n",
|
||
"B-UNIT 44 || \n",
|
||
"I-UNIT 1 || \n",
|
||
"I-MAT 16 || \n",
|
||
"I-QUANT 1 || \n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"data = []\n",
|
||
"with open(\"../dataset/new_ner_srl.tsv\", encoding=\"utf-8\") as f:\n",
|
||
"# with open(\"../dataset/test_ns_dataset.tsv\", encoding=\"utf-8\") as f:\n",
|
||
" tok, ner, srl = [], [], []\n",
|
||
" for line in f:\n",
|
||
" line = line.strip()\n",
|
||
" if not line:\n",
|
||
" if tok:\n",
|
||
" data.append({\"tokens\": tok, \"labels_ner\": ner, \"labels_srl\": srl})\n",
|
||
" tok, ner, srl = [], [], []\n",
|
||
" else:\n",
|
||
" t, n, s = line.split(\"\\t\")\n",
|
||
" tok.append(t.lower())\n",
|
||
" ner.append(n.strip())\n",
|
||
" srl.append(s.strip())\n",
|
||
"\n",
|
||
"print(\"total kalimat \", len(data))\n",
|
||
"# ——————————————————\n",
|
||
"sentences = [d[\"tokens\"] for d in data]\n",
|
||
"labels_ner = [d[\"labels_ner\"] for d in data]\n",
|
||
"labels_srl = [d[\"labels_srl\"] for d in data]\n",
|
||
"\n",
|
||
"ner_counter = Counter(label for seq in labels_ner for label in seq)\n",
|
||
"\n",
|
||
"srl_counter = Counter(label for seq in labels_srl for label in seq)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"{'NER Label':<15} {'Count':<10} || {'SRL Label':<15} {'Count':<10}\")\n",
|
||
"print(\"-\" * 55)\n",
|
||
"\n",
|
||
"for (ner_label, ner_count), (srl_label, srl_count) in zip_longest(ner_counter.items(), srl_counter.items(), fillvalue=('', '')):\n",
|
||
" print(f\"{ner_label:<15} {ner_count:<10} || {srl_label:<15} {srl_count:<10}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 118,
|
||
"id": "8dda2d6c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"NER -> Total Labels: 12425, O Count: 7261, O Percentage: 58.44%\n",
|
||
"SRL -> Total Labels: 12425, O Count: 4182, O Percentage: 33.66%\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"\n",
|
||
"\n",
|
||
"def calculate_o_percentage(labels):\n",
|
||
" counter = Counter(label for seq in labels for label in seq)\n",
|
||
" total = sum(counter.values())\n",
|
||
" count_o = counter.get(\"O\", 0)\n",
|
||
" percent_o = (count_o / total) * 100 if total > 0 else 0\n",
|
||
" return percent_o, total, count_o\n",
|
||
"\n",
|
||
"# Hitung persentase 'O' untuk NER\n",
|
||
"o_ner_percent, total_ner, o_ner_count = calculate_o_percentage(labels_ner)\n",
|
||
"\n",
|
||
"# Hitung persentase 'O' untuk SRL\n",
|
||
"o_srl_percent, total_srl, o_srl_count = calculate_o_percentage(labels_srl)\n",
|
||
"\n",
|
||
"print(f\"NER -> Total Labels: {total_ner}, O Count: {o_ner_count}, O Percentage: {o_ner_percent:.2f}%\")\n",
|
||
"print(f\"SRL -> Total Labels: {total_srl}, O Count: {o_srl_count}, O Percentage: {o_srl_percent:.2f}%\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 119,
|
||
"id": "48553e6b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"PAD_TOKEN = \"<PAD>\"\n",
|
||
"words = sorted({w for s in sentences for w in s})\n",
|
||
"\n",
|
||
"ner_tags = sorted({t for seq in labels_ner for t in seq})\n",
|
||
"srl_tags = sorted({t for seq in labels_srl for t in seq})\n",
|
||
"\n",
|
||
"ner_tags.insert(0, PAD_TOKEN)\n",
|
||
"srl_tags.insert(0, PAD_TOKEN)\n",
|
||
"\n",
|
||
"word2idx = {w: i + 2 for i, w in enumerate(words)}\n",
|
||
"word2idx[\"PAD\"] = 0\n",
|
||
"word2idx[\"UNK\"] = 1\n",
|
||
"\n",
|
||
"tag2idx_ner = {t: i for i, t in enumerate(ner_tags)}\n",
|
||
"tag2idx_srl = {t: i for i, t in enumerate(srl_tags)}\n",
|
||
"idx2tag_ner = {i: t for t, i in tag2idx_ner.items()}\n",
|
||
"idx2tag_srl = {i: t for t, i in tag2idx_srl.items()}"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 120,
|
||
"id": "096967e8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"X = [[word2idx.get(w, 1) for w in s] for s in sentences]\n",
|
||
"y_ner = [[tag2idx_ner[t] for t in seq] for seq in labels_ner]\n",
|
||
"y_srl = [[tag2idx_srl[t] for t in seq] for seq in labels_srl]\n",
|
||
"\n",
|
||
"maxlen = max(map(len, X))\n",
|
||
"pad_id = tag2idx_ner[PAD_TOKEN]\n",
|
||
"\n",
|
||
"X = pad_sequences(X, maxlen=maxlen, padding=\"post\", value=0)\n",
|
||
"y_ner = pad_sequences(y_ner, maxlen=maxlen, padding=\"post\", value=pad_id)\n",
|
||
"y_srl = pad_sequences(y_srl, maxlen=maxlen, padding=\"post\", value=pad_id)\n",
|
||
"\n",
|
||
"mask = (y_ner != pad_id).astype(\"float32\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 121,
|
||
"id": "a26893cc",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"splits = train_test_split(\n",
|
||
" X, y_ner, y_srl, mask, test_size=0.2, random_state=42, shuffle=True\n",
|
||
")\n",
|
||
"X_tr, X_te, ner_tr, ner_te, srl_tr, srl_te, m_tr, m_te = splits"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 122,
|
||
"id": "1b4a1c61",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_7\"</span>\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1mModel: \"functional_7\"\u001b[0m\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
|
||
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃<span style=\"font-weight: bold\"> Connected to </span>┃\n",
|
||
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
||
"│ tokens (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ - │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ embed (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">87,296</span> │ tokens[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ spatial_dropout1d_7 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ embed[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">SpatialDropout1D</span>) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ not_equal_7 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ tokens[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">NotEqual</span>) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional_14 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">66,048</span> │ spatial_dropout1… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Bidirectional</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional_15 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">98,816</span> │ bidirectional_14… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Bidirectional</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ time_distributed_14 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │ bidirectional_15… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ time_distributed_15 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">8,256</span> │ bidirectional_15… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ ner_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,560</span> │ time_distributed… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ srl_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">34</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">13</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">845</span> │ time_distributed… │\n",
|
||
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ not_equal_7[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
||
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
|
||
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
|
||
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
||
"│ tokens (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ embed (\u001b[38;5;33mEmbedding\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m87,296\u001b[0m │ tokens[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ spatial_dropout1d_7 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ embed[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"│ (\u001b[38;5;33mSpatialDropout1D\u001b[0m) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ not_equal_7 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ tokens[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"│ (\u001b[38;5;33mNotEqual\u001b[0m) │ │ │ │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional_14 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m66,048\u001b[0m │ spatial_dropout1… │\n",
|
||
"│ (\u001b[38;5;33mBidirectional\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ bidirectional_15 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m98,816\u001b[0m │ bidirectional_14… │\n",
|
||
"│ (\u001b[38;5;33mBidirectional\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ time_distributed_14 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m8,256\u001b[0m │ bidirectional_15… │\n",
|
||
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ time_distributed_15 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m8,256\u001b[0m │ bidirectional_15… │\n",
|
||
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ ner_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m24\u001b[0m) │ \u001b[38;5;34m1,560\u001b[0m │ time_distributed… │\n",
|
||
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
||
"│ srl_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m13\u001b[0m) │ \u001b[38;5;34m845\u001b[0m │ time_distributed… │\n",
|
||
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ not_equal_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
||
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">271,077</span> (1.03 MB)\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m271,077\u001b[0m (1.03 MB)\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">271,077</span> (1.03 MB)\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m271,077\u001b[0m (1.03 MB)\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
|
||
"</pre>\n"
|
||
],
|
||
"text/plain": [
|
||
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"embed_dim = 64\n",
|
||
"lstm_units = 64\n",
|
||
"drop_embed = 0.5\n",
|
||
"drop_lstm = 0.5\n",
|
||
"\n",
|
||
"inp = Input(shape=(maxlen,), name=\"tokens\")\n",
|
||
"emb = Embedding(len(word2idx), embed_dim, mask_zero=True, name=\"embed\")(inp)\n",
|
||
"emb = SpatialDropout1D(drop_embed)(emb)\n",
|
||
"\n",
|
||
"x = Bidirectional(\n",
|
||
" LSTM(\n",
|
||
" lstm_units,\n",
|
||
" return_sequences=True,\n",
|
||
" dropout=drop_lstm,\n",
|
||
" recurrent_dropout=drop_lstm,\n",
|
||
" )\n",
|
||
")(emb)\n",
|
||
"x = Bidirectional(\n",
|
||
" LSTM(\n",
|
||
" lstm_units,\n",
|
||
" return_sequences=True,\n",
|
||
" dropout=drop_lstm,\n",
|
||
" recurrent_dropout=drop_lstm,\n",
|
||
" )\n",
|
||
")(x)\n",
|
||
"\n",
|
||
"ner_head = TimeDistributed(Dense(lstm_units, activation=\"relu\"))(x)\n",
|
||
"ner_out = TimeDistributed(\n",
|
||
" Dense(len(tag2idx_ner), activation=\"softmax\"), name=\"ner_output\"\n",
|
||
")(ner_head)\n",
|
||
"\n",
|
||
"srl_head = TimeDistributed(Dense(lstm_units, activation=\"relu\"))(x)\n",
|
||
"srl_out = TimeDistributed(\n",
|
||
" Dense(len(tag2idx_srl), activation=\"softmax\"), name=\"srl_output\"\n",
|
||
")(srl_head)\n",
|
||
"\n",
|
||
"model = Model(inp, [ner_out, srl_out])\n",
|
||
"\n",
|
||
"model.compile(\n",
|
||
" optimizer=tf.keras.optimizers.Adam(3e-4),\n",
|
||
" loss={\n",
|
||
" \"ner_output\": \"sparse_categorical_crossentropy\",\n",
|
||
" \"srl_output\": \"sparse_categorical_crossentropy\",\n",
|
||
" },\n",
|
||
" metrics={\n",
|
||
" \"ner_output\": [\"sparse_categorical_accuracy\"],\n",
|
||
" \"srl_output\": [\"sparse_categorical_accuracy\"],\n",
|
||
" },\n",
|
||
" # sample_weight_mode=\"temporal\"\n",
|
||
")\n",
|
||
"model.summary()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 123,
|
||
"id": "f41d6012",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Epoch 1/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m10s\u001b[0m 105ms/step - loss: 5.7110 - ner_output_loss: 3.1579 - ner_output_sparse_categorical_accuracy: 0.2067 - srl_output_loss: 2.5530 - srl_output_sparse_categorical_accuracy: 0.1810 - val_loss: 5.5840 - val_ner_output_loss: 3.0747 - val_ner_output_sparse_categorical_accuracy: 0.1325 - val_srl_output_loss: 2.5086 - val_srl_output_sparse_categorical_accuracy: 0.0750 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 2/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 5.4576 - ner_output_loss: 2.9911 - ner_output_sparse_categorical_accuracy: 0.1311 - srl_output_loss: 2.4653 - srl_output_sparse_categorical_accuracy: 0.0760 - val_loss: 4.6826 - val_ner_output_loss: 2.4715 - val_ner_output_sparse_categorical_accuracy: 0.1325 - val_srl_output_loss: 2.1957 - val_srl_output_sparse_categorical_accuracy: 0.0750 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 3/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 4.3203 - ner_output_loss: 2.2263 - ner_output_sparse_categorical_accuracy: 0.1270 - srl_output_loss: 2.0936 - srl_output_sparse_categorical_accuracy: 0.0751 - val_loss: 3.6358 - val_ner_output_loss: 1.8780 - val_ner_output_sparse_categorical_accuracy: 0.1325 - val_srl_output_loss: 1.7769 - val_srl_output_sparse_categorical_accuracy: 0.1032 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 4/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 3.4818 - ner_output_loss: 1.7297 - ner_output_sparse_categorical_accuracy: 0.1284 - srl_output_loss: 1.7518 - srl_output_sparse_categorical_accuracy: 0.1028 - val_loss: 3.0980 - val_ner_output_loss: 1.5394 - val_ner_output_sparse_categorical_accuracy: 0.1325 - val_srl_output_loss: 1.5650 - val_srl_output_sparse_categorical_accuracy: 0.1015 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 5/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 42ms/step - loss: 3.0010 - ner_output_loss: 1.4352 - ner_output_sparse_categorical_accuracy: 0.1320 - srl_output_loss: 1.5651 - srl_output_sparse_categorical_accuracy: 0.1053 - val_loss: 2.7911 - val_ner_output_loss: 1.3675 - val_ner_output_sparse_categorical_accuracy: 0.1383 - val_srl_output_loss: 1.4193 - val_srl_output_sparse_categorical_accuracy: 0.1185 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 6/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 42ms/step - loss: 2.6586 - ner_output_loss: 1.2858 - ner_output_sparse_categorical_accuracy: 0.1416 - srl_output_loss: 1.3731 - srl_output_sparse_categorical_accuracy: 0.1208 - val_loss: 2.5715 - val_ner_output_loss: 1.2498 - val_ner_output_sparse_categorical_accuracy: 0.1475 - val_srl_output_loss: 1.3092 - val_srl_output_sparse_categorical_accuracy: 0.1243 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 7/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 42ms/step - loss: 2.5278 - ner_output_loss: 1.1977 - ner_output_sparse_categorical_accuracy: 0.1510 - srl_output_loss: 1.3293 - srl_output_sparse_categorical_accuracy: 0.1260 - val_loss: 2.4185 - val_ner_output_loss: 1.1771 - val_ner_output_sparse_categorical_accuracy: 0.1486 - val_srl_output_loss: 1.2246 - val_srl_output_sparse_categorical_accuracy: 0.1286 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 8/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 2.3210 - ner_output_loss: 1.1242 - ner_output_sparse_categorical_accuracy: 0.1475 - srl_output_loss: 1.1972 - srl_output_sparse_categorical_accuracy: 0.1244 - val_loss: 2.3181 - val_ner_output_loss: 1.1293 - val_ner_output_sparse_categorical_accuracy: 0.1491 - val_srl_output_loss: 1.1701 - val_srl_output_sparse_categorical_accuracy: 0.1266 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 9/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 42ms/step - loss: 2.1532 - ner_output_loss: 1.0439 - ner_output_sparse_categorical_accuracy: 0.1456 - srl_output_loss: 1.1101 - srl_output_sparse_categorical_accuracy: 0.1250 - val_loss: 2.2397 - val_ner_output_loss: 1.0935 - val_ner_output_sparse_categorical_accuracy: 0.1491 - val_srl_output_loss: 1.1276 - val_srl_output_sparse_categorical_accuracy: 0.1466 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 10/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 2.1745 - ner_output_loss: 1.0467 - ner_output_sparse_categorical_accuracy: 0.1509 - srl_output_loss: 1.1280 - srl_output_sparse_categorical_accuracy: 0.1340 - val_loss: 2.1663 - val_ner_output_loss: 1.0578 - val_ner_output_sparse_categorical_accuracy: 0.1653 - val_srl_output_loss: 1.0900 - val_srl_output_sparse_categorical_accuracy: 0.1437 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 11/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 2.0726 - ner_output_loss: 1.0098 - ner_output_sparse_categorical_accuracy: 0.1532 - srl_output_loss: 1.0632 - srl_output_sparse_categorical_accuracy: 0.1427 - val_loss: 2.0905 - val_ner_output_loss: 1.0194 - val_ner_output_sparse_categorical_accuracy: 0.1656 - val_srl_output_loss: 1.0506 - val_srl_output_sparse_categorical_accuracy: 0.1483 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 12/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.9597 - ner_output_loss: 0.9479 - ner_output_sparse_categorical_accuracy: 0.1595 - srl_output_loss: 1.0113 - srl_output_sparse_categorical_accuracy: 0.1466 - val_loss: 2.0062 - val_ner_output_loss: 0.9765 - val_ner_output_sparse_categorical_accuracy: 0.1654 - val_srl_output_loss: 1.0097 - val_srl_output_sparse_categorical_accuracy: 0.1526 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 13/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.9171 - ner_output_loss: 0.9401 - ner_output_sparse_categorical_accuracy: 0.1655 - srl_output_loss: 0.9774 - srl_output_sparse_categorical_accuracy: 0.1519 - val_loss: 1.9191 - val_ner_output_loss: 0.9321 - val_ner_output_sparse_categorical_accuracy: 0.1659 - val_srl_output_loss: 0.9655 - val_srl_output_sparse_categorical_accuracy: 0.1561 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 14/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.8593 - ner_output_loss: 0.9060 - ner_output_sparse_categorical_accuracy: 0.1702 - srl_output_loss: 0.9529 - srl_output_sparse_categorical_accuracy: 0.1545 - val_loss: 1.8181 - val_ner_output_loss: 0.8752 - val_ner_output_sparse_categorical_accuracy: 0.1736 - val_srl_output_loss: 0.9142 - val_srl_output_sparse_categorical_accuracy: 0.1606 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 15/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 43ms/step - loss: 1.7053 - ner_output_loss: 0.8312 - ner_output_sparse_categorical_accuracy: 0.1694 - srl_output_loss: 0.8744 - srl_output_sparse_categorical_accuracy: 0.1578 - val_loss: 1.7062 - val_ner_output_loss: 0.8141 - val_ner_output_sparse_categorical_accuracy: 0.1768 - val_srl_output_loss: 0.8590 - val_srl_output_sparse_categorical_accuracy: 0.1690 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 16/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.5892 - ner_output_loss: 0.7715 - ner_output_sparse_categorical_accuracy: 0.1733 - srl_output_loss: 0.8177 - srl_output_sparse_categorical_accuracy: 0.1628 - val_loss: 1.5958 - val_ner_output_loss: 0.7575 - val_ner_output_sparse_categorical_accuracy: 0.1785 - val_srl_output_loss: 0.8016 - val_srl_output_sparse_categorical_accuracy: 0.1699 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 17/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.5047 - ner_output_loss: 0.7224 - ner_output_sparse_categorical_accuracy: 0.1762 - srl_output_loss: 0.7827 - srl_output_sparse_categorical_accuracy: 0.1656 - val_loss: 1.4978 - val_ner_output_loss: 0.7097 - val_ner_output_sparse_categorical_accuracy: 0.1848 - val_srl_output_loss: 0.7469 - val_srl_output_sparse_categorical_accuracy: 0.1730 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 18/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 44ms/step - loss: 1.4376 - ner_output_loss: 0.6999 - ner_output_sparse_categorical_accuracy: 0.1783 - srl_output_loss: 0.7377 - srl_output_sparse_categorical_accuracy: 0.1696 - val_loss: 1.4164 - val_ner_output_loss: 0.6699 - val_ner_output_sparse_categorical_accuracy: 0.1860 - val_srl_output_loss: 0.7027 - val_srl_output_sparse_categorical_accuracy: 0.1755 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 19/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 1.3140 - ner_output_loss: 0.6430 - ner_output_sparse_categorical_accuracy: 0.1816 - srl_output_loss: 0.6698 - srl_output_sparse_categorical_accuracy: 0.1733 - val_loss: 1.3554 - val_ner_output_loss: 0.6392 - val_ner_output_sparse_categorical_accuracy: 0.1888 - val_srl_output_loss: 0.6697 - val_srl_output_sparse_categorical_accuracy: 0.1776 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 20/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.2762 - ner_output_loss: 0.6169 - ner_output_sparse_categorical_accuracy: 0.1809 - srl_output_loss: 0.6601 - srl_output_sparse_categorical_accuracy: 0.1729 - val_loss: 1.2996 - val_ner_output_loss: 0.6101 - val_ner_output_sparse_categorical_accuracy: 0.1901 - val_srl_output_loss: 0.6401 - val_srl_output_sparse_categorical_accuracy: 0.1794 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 21/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.2447 - ner_output_loss: 0.6027 - ner_output_sparse_categorical_accuracy: 0.1849 - srl_output_loss: 0.6418 - srl_output_sparse_categorical_accuracy: 0.1760 - val_loss: 1.2591 - val_ner_output_loss: 0.5895 - val_ner_output_sparse_categorical_accuracy: 0.1897 - val_srl_output_loss: 0.6165 - val_srl_output_sparse_categorical_accuracy: 0.1797 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 22/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 1.1679 - ner_output_loss: 0.5572 - ner_output_sparse_categorical_accuracy: 0.1878 - srl_output_loss: 0.6102 - srl_output_sparse_categorical_accuracy: 0.1781 - val_loss: 1.2209 - val_ner_output_loss: 0.5655 - val_ner_output_sparse_categorical_accuracy: 0.1910 - val_srl_output_loss: 0.5995 - val_srl_output_sparse_categorical_accuracy: 0.1813 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 23/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 1.0996 - ner_output_loss: 0.5274 - ner_output_sparse_categorical_accuracy: 0.1873 - srl_output_loss: 0.5710 - srl_output_sparse_categorical_accuracy: 0.1794 - val_loss: 1.1831 - val_ner_output_loss: 0.5454 - val_ner_output_sparse_categorical_accuracy: 0.1924 - val_srl_output_loss: 0.5802 - val_srl_output_sparse_categorical_accuracy: 0.1821 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 24/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 1.1842 - ner_output_loss: 0.5630 - ner_output_sparse_categorical_accuracy: 0.1890 - srl_output_loss: 0.6211 - srl_output_sparse_categorical_accuracy: 0.1791 - val_loss: 1.1559 - val_ner_output_loss: 0.5311 - val_ner_output_sparse_categorical_accuracy: 0.1940 - val_srl_output_loss: 0.5664 - val_srl_output_sparse_categorical_accuracy: 0.1832 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 25/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 44ms/step - loss: 1.0526 - ner_output_loss: 0.5143 - ner_output_sparse_categorical_accuracy: 0.1923 - srl_output_loss: 0.5390 - srl_output_sparse_categorical_accuracy: 0.1856 - val_loss: 1.1268 - val_ner_output_loss: 0.5145 - val_ner_output_sparse_categorical_accuracy: 0.1958 - val_srl_output_loss: 0.5533 - val_srl_output_sparse_categorical_accuracy: 0.1842 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 26/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 47ms/step - loss: 1.0331 - ner_output_loss: 0.4892 - ner_output_sparse_categorical_accuracy: 0.1884 - srl_output_loss: 0.5446 - srl_output_sparse_categorical_accuracy: 0.1805 - val_loss: 1.1003 - val_ner_output_loss: 0.4994 - val_ner_output_sparse_categorical_accuracy: 0.1966 - val_srl_output_loss: 0.5411 - val_srl_output_sparse_categorical_accuracy: 0.1845 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 27/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 45ms/step - loss: 0.9729 - ner_output_loss: 0.4579 - ner_output_sparse_categorical_accuracy: 0.1902 - srl_output_loss: 0.5148 - srl_output_sparse_categorical_accuracy: 0.1837 - val_loss: 1.0818 - val_ner_output_loss: 0.4883 - val_ner_output_sparse_categorical_accuracy: 0.1967 - val_srl_output_loss: 0.5338 - val_srl_output_sparse_categorical_accuracy: 0.1851 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 28/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 44ms/step - loss: 0.9333 - ner_output_loss: 0.4367 - ner_output_sparse_categorical_accuracy: 0.1909 - srl_output_loss: 0.4970 - srl_output_sparse_categorical_accuracy: 0.1826 - val_loss: 1.0529 - val_ner_output_loss: 0.4698 - val_ner_output_sparse_categorical_accuracy: 0.2007 - val_srl_output_loss: 0.5223 - val_srl_output_sparse_categorical_accuracy: 0.1865 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 29/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 1.0398 - ner_output_loss: 0.4866 - ner_output_sparse_categorical_accuracy: 0.1948 - srl_output_loss: 0.5531 - srl_output_sparse_categorical_accuracy: 0.1833 - val_loss: 1.0380 - val_ner_output_loss: 0.4601 - val_ner_output_sparse_categorical_accuracy: 0.1998 - val_srl_output_loss: 0.5154 - val_srl_output_sparse_categorical_accuracy: 0.1870 - learning_rate: 3.0000e-04\n",
|
||
"Epoch 30/30\n",
|
||
"\u001b[1m21/21\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 46ms/step - loss: 0.9113 - ner_output_loss: 0.4297 - ner_output_sparse_categorical_accuracy: 0.1923 - srl_output_loss: 0.4818 - srl_output_sparse_categorical_accuracy: 0.1842 - val_loss: 1.0241 - val_ner_output_loss: 0.4523 - val_ner_output_sparse_categorical_accuracy: 0.2027 - val_srl_output_loss: 0.5074 - val_srl_output_sparse_categorical_accuracy: 0.1870 - learning_rate: 3.0000e-04\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"callbacks = [\n",
|
||
" tf.keras.callbacks.EarlyStopping(patience=3, restore_best_weights=True),\n",
|
||
" tf.keras.callbacks.ReduceLROnPlateau(patience=2, factor=0.5, min_lr=1e-5),\n",
|
||
"]\n",
|
||
"\n",
|
||
"history = model.fit(\n",
|
||
" X_tr,\n",
|
||
" [ner_tr, srl_tr], # y → LIST (pos 0 = ner_output, 1 = srl_output)\n",
|
||
" sample_weight=[m_tr, m_tr], # sama‑persis urutan\n",
|
||
" validation_data=(X_te, [ner_te, srl_te], [m_te, m_te]),\n",
|
||
" \n",
|
||
" batch_size=64,\n",
|
||
" epochs=30,\n",
|
||
" callbacks=callbacks,\n",
|
||
" verbose=1,\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"# =========================\n",
|
||
"# 7. Save artefacts\n",
|
||
"# =========================\n",
|
||
"model.save(\"lstm_ner_srl_model.keras\")\n",
|
||
"for fname, obj in [\n",
|
||
" (\"word2idx.pkl\", word2idx),\n",
|
||
" (\"tag2idx_ner.pkl\", tag2idx_ner),\n",
|
||
" (\"tag2idx_srl.pkl\", tag2idx_srl),\n",
|
||
"]:\n",
|
||
" with open(fname, \"wb\") as f:\n",
|
||
" pickle.dump(obj, f)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 124,
|
||
"id": "430794b9",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"def plot_training_history(history):\n",
|
||
" history_data = history.history\n",
|
||
" epochs = range(1, len(next(iter(history_data.values()))) + 1)\n",
|
||
"\n",
|
||
" # Coba deteksi metric secara dinamis agar fleksibel\n",
|
||
" ner_acc_key = next((k for k in history_data if \"ner_output\" in k and \"accuracy\" in k), None)\n",
|
||
" srl_acc_key = next((k for k in history_data if \"srl_output\" in k and \"accuracy\" in k), None)\n",
|
||
" val_ner_acc_key = f\"val_{ner_acc_key}\" if ner_acc_key else None\n",
|
||
" val_srl_acc_key = f\"val_{srl_acc_key}\" if srl_acc_key else None\n",
|
||
"\n",
|
||
" # --- Plot Accuracy ---\n",
|
||
" plt.figure(figsize=(10, 6))\n",
|
||
" if ner_acc_key:\n",
|
||
" plt.plot(epochs, history_data[ner_acc_key], marker=\"o\", label=\"NER Accuracy (Train)\")\n",
|
||
" if srl_acc_key:\n",
|
||
" plt.plot(epochs, history_data[srl_acc_key], marker=\"s\", label=\"SRL Accuracy (Train)\")\n",
|
||
" if val_ner_acc_key in history_data:\n",
|
||
" plt.plot(epochs, history_data[val_ner_acc_key], marker=\"o\", linestyle=\"--\", label=\"NER Accuracy (Val)\")\n",
|
||
" if val_srl_acc_key in history_data:\n",
|
||
" plt.plot(epochs, history_data[val_srl_acc_key], marker=\"s\", linestyle=\"--\", label=\"SRL Accuracy (Val)\")\n",
|
||
"\n",
|
||
" plt.title(\"Accuracy per Epoch\")\n",
|
||
" plt.xlabel(\"Epochs\")\n",
|
||
" plt.ylabel(\"Accuracy\")\n",
|
||
" plt.legend()\n",
|
||
" plt.grid(True)\n",
|
||
" plt.savefig(\"accuracy_plot.png\")\n",
|
||
" plt.show()\n",
|
||
"\n",
|
||
" # --- Plot Loss ---\n",
|
||
" plt.figure(figsize=(10, 6))\n",
|
||
" if \"ner_output_loss\" in history_data:\n",
|
||
" plt.plot(epochs, history_data[\"ner_output_loss\"], marker=\"o\", label=\"NER Loss (Train)\")\n",
|
||
" if \"srl_output_loss\" in history_data:\n",
|
||
" plt.plot(epochs, history_data[\"srl_output_loss\"], marker=\"s\", label=\"SRL Loss (Train)\")\n",
|
||
" if \"val_ner_output_loss\" in history_data:\n",
|
||
" plt.plot(epochs, history_data[\"val_ner_output_loss\"], marker=\"o\", linestyle=\"--\", label=\"NER Loss (Val)\")\n",
|
||
" if \"val_srl_output_loss\" in history_data:\n",
|
||
" plt.plot(epochs, history_data[\"val_srl_output_loss\"], marker=\"s\", linestyle=\"--\", label=\"SRL Loss (Val)\")\n",
|
||
"\n",
|
||
" plt.title(\"Loss per Epoch\")\n",
|
||
" plt.xlabel(\"Epochs\")\n",
|
||
" plt.ylabel(\"Loss\")\n",
|
||
" plt.legend()\n",
|
||
" plt.grid(True)\n",
|
||
" plt.savefig(\"loss_plot.png\")\n",
|
||
" plt.show()\n",
|
||
"\n",
|
||
"\n",
|
||
"plot_training_history(history)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 125,
|
||
"id": "e690a0e0",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x1000 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x1000 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import matplotlib.pyplot as plt\n",
|
||
"from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 1. Prediksi\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"pred_ner_prob, pred_srl_prob = model.predict(X_te, verbose=0)\n",
|
||
"\n",
|
||
"pred_ner = pred_ner_prob.argmax(-1)\n",
|
||
"pred_srl = pred_srl_prob.argmax(-1)\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 2. Siapkan masker PAD\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"pad_id = tag2idx_ner[\"<PAD>\"]\n",
|
||
"\n",
|
||
"mask_ner = ner_te != pad_id\n",
|
||
"mask_srl = srl_te != pad_id\n",
|
||
"\n",
|
||
"true_ner_flat = ner_te[mask_ner]\n",
|
||
"pred_ner_flat = pred_ner[mask_ner]\n",
|
||
"\n",
|
||
"true_srl_flat = srl_te[mask_srl]\n",
|
||
"pred_srl_flat = pred_srl[mask_srl]\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 3. Hitung confusion matrix TANPA PAD\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# Buang ID PAD dari label list\n",
|
||
"labels_ner_no_pad = [i for i in range(len(tag2idx_ner)) if i != pad_id]\n",
|
||
"labels_srl_no_pad = [i for i in range(len(tag2idx_srl)) if i != pad_id]\n",
|
||
"\n",
|
||
"cm_ner = confusion_matrix(true_ner_flat, pred_ner_flat, labels=labels_ner_no_pad)\n",
|
||
"\n",
|
||
"cm_srl = confusion_matrix(true_srl_flat, pred_srl_flat, labels=labels_srl_no_pad)\n",
|
||
"\n",
|
||
"# Siapkan label display TANPA PAD\n",
|
||
"display_labels_ner = [idx2tag_ner[i] for i in labels_ner_no_pad]\n",
|
||
"display_labels_srl = [idx2tag_srl[i] for i in labels_srl_no_pad]\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 4. Plot NER CM (tanpa PAD)\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"fig, ax = plt.subplots(figsize=(10, 10))\n",
|
||
"disp_ner = ConfusionMatrixDisplay(\n",
|
||
" confusion_matrix=cm_ner, display_labels=display_labels_ner\n",
|
||
")\n",
|
||
"disp_ner.plot(\n",
|
||
" include_values=True, # Tampilkan angka\n",
|
||
" values_format=\"d\", # Format integer\n",
|
||
" cmap=plt.cm.Blues, # Biru-putih\n",
|
||
" ax=ax,\n",
|
||
" colorbar=False,\n",
|
||
")\n",
|
||
"ax.set_title(\"NER Confusion Matrix\", fontsize=18)\n",
|
||
"plt.setp(ax.get_xticklabels(), rotation=45, ha=\"right\")\n",
|
||
"plt.tight_layout()\n",
|
||
"plt.show()\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 5. Plot SRL CM (tanpa PAD)\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"fig, ax = plt.subplots(figsize=(10, 10))\n",
|
||
"disp_srl = ConfusionMatrixDisplay(\n",
|
||
" confusion_matrix=cm_srl, display_labels=display_labels_srl\n",
|
||
")\n",
|
||
"disp_srl.plot(\n",
|
||
" include_values=True, values_format=\"d\", cmap=plt.cm.Blues, ax=ax, colorbar=False\n",
|
||
")\n",
|
||
"ax.set_title(\"SRL Confusion Matrix\", fontsize=18)\n",
|
||
"plt.setp(ax.get_xticklabels(), rotation=45, ha=\"right\")\n",
|
||
"plt.tight_layout()\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 126,
|
||
"id": "a49f1dfe",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"NER TAG accuracy : 88.84%\n",
|
||
"SRL TAG accuracy : 81.93%\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from sklearn.metrics import accuracy_score, classification_report\n",
|
||
"\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"# 3b. Akurasi token‑level (tanpa PAD)\n",
|
||
"# ------------------------------------------------------------------\n",
|
||
"acc_ner = accuracy_score(true_ner_flat, pred_ner_flat)\n",
|
||
"acc_srl = accuracy_score(true_srl_flat, pred_srl_flat)\n",
|
||
"\n",
|
||
"print(f\"NER TAG accuracy : {acc_ner:.2%}\")\n",
|
||
"print(f\"SRL TAG accuracy : {acc_srl:.2%}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 127,
|
||
"id": "9adad755",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"[NER] Classification report:\n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" B-DATE 0.84 0.93 0.89 75\n",
|
||
" B-ETH 0.78 0.80 0.79 45\n",
|
||
" B-EVENT 0.00 0.00 0.00 14\n",
|
||
" B-LOC 0.94 0.90 0.92 304\n",
|
||
" B-MAT 0.00 0.00 0.00 19\n",
|
||
" B-MISC 0.00 0.00 0.00 6\n",
|
||
" B-ORG 0.00 0.00 0.00 2\n",
|
||
" B-PER 0.87 0.93 0.90 248\n",
|
||
" B-QUANT 0.00 0.00 0.00 11\n",
|
||
" B-TIME 0.00 0.00 0.00 49\n",
|
||
" B-UNIT 0.00 0.00 0.00 11\n",
|
||
" I-DATE 0.82 0.98 0.89 146\n",
|
||
" I-ETH 0.89 0.70 0.78 46\n",
|
||
" I-EVENT 0.00 0.00 0.00 8\n",
|
||
" I-LOC 0.00 0.00 0.00 8\n",
|
||
" I-MAT 0.00 0.00 0.00 2\n",
|
||
" I-MISC 0.00 0.00 0.00 1\n",
|
||
" I-ORG 0.00 0.00 0.00 1\n",
|
||
" I-PER 0.69 0.65 0.67 51\n",
|
||
" I-QUANT 0.00 0.00 0.00 0\n",
|
||
" I-TIME 0.00 0.00 0.00 19\n",
|
||
" I-UNIT 0.00 0.00 0.00 1\n",
|
||
" O 0.90 0.98 0.94 1478\n",
|
||
"\n",
|
||
" accuracy 0.89 2545\n",
|
||
" macro avg 0.29 0.30 0.29 2545\n",
|
||
"weighted avg 0.84 0.89 0.86 2545\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no true nor predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no true nor predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Recall is ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no true nor predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# (Opsional) tampilkan ringkasan metrik per‑label\n",
|
||
"print(\"\\n[NER] Classification report:\")\n",
|
||
"print(\n",
|
||
" classification_report(\n",
|
||
" true_ner_flat,\n",
|
||
" pred_ner_flat,\n",
|
||
" labels=labels_ner_no_pad,\n",
|
||
" target_names=display_labels_ner,\n",
|
||
" digits=2,\n",
|
||
" )\n",
|
||
")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 128,
|
||
"id": "7cd28380",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\n",
|
||
"[SRL] Classification report:\n",
|
||
" precision recall f1-score support\n",
|
||
"\n",
|
||
" ARG0 0.81 0.93 0.87 396\n",
|
||
" ARG1 0.61 0.60 0.60 288\n",
|
||
" ARG2 0.27 0.33 0.30 54\n",
|
||
" ARGM-CAU 0.00 0.00 0.00 4\n",
|
||
" ARGM-DIR 0.00 0.00 0.00 11\n",
|
||
" ARGM-LOC 0.88 0.87 0.87 296\n",
|
||
" ARGM-MNR 0.00 0.00 0.00 7\n",
|
||
" ARGM-MOD 0.00 0.00 0.00 8\n",
|
||
" ARGM-NEG 0.00 0.00 0.00 1\n",
|
||
" ARGM-TMP 0.83 0.82 0.83 302\n",
|
||
" O 0.89 0.89 0.89 836\n",
|
||
" V 0.89 0.80 0.84 342\n",
|
||
"\n",
|
||
" accuracy 0.82 2545\n",
|
||
" macro avg 0.43 0.44 0.43 2545\n",
|
||
"weighted avg 0.81 0.82 0.82 2545\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n",
|
||
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
||
" _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"\\n[SRL] Classification report:\")\n",
|
||
"print(\n",
|
||
" classification_report(\n",
|
||
" true_srl_flat,\n",
|
||
" pred_srl_flat,\n",
|
||
" labels=labels_srl_no_pad,\n",
|
||
" target_names=display_labels_srl,\n",
|
||
" digits=2,\n",
|
||
" )\n",
|
||
")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 129,
|
||
"id": "333745fd",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# def plot_training_history(history):\n",
|
||
"# epochs = range(1, len(history['loss']) + 1)\n",
|
||
"\n",
|
||
"# plt.figure(figsize=(14, 6))\n",
|
||
"\n",
|
||
"# # Plot Loss\n",
|
||
"# plt.subplot(1, 2, 1)\n",
|
||
"# plt.plot(epochs, history['loss'], label='Training Loss')\n",
|
||
"# plt.plot(epochs, history['val_loss'], label='Validation Loss')\n",
|
||
"# plt.title('Loss During Training')\n",
|
||
"# plt.xlabel('Epochs')\n",
|
||
"# plt.ylabel('Loss')\n",
|
||
"# plt.legend()\n",
|
||
"\n",
|
||
"# # Plot Accuracy\n",
|
||
"# plt.subplot(1, 2, 2)\n",
|
||
"# plt.plot(epochs, history['ner_output_accuracy'], label='NER Train Acc')\n",
|
||
"# plt.plot(epochs, history['val_ner_output_accuracy'], label='NER Val Acc')\n",
|
||
"# plt.plot(epochs, history['srl_output_accuracy'], label='SRL Train Acc')\n",
|
||
"# plt.plot(epochs, history['val_srl_output_accuracy'], label='SRL Val Acc')\n",
|
||
"# plt.title('Accuracy During Training')\n",
|
||
"# plt.xlabel('Epochs')\n",
|
||
"# plt.ylabel('Accuracy')\n",
|
||
"# plt.legend()\n",
|
||
"\n",
|
||
"# plt.tight_layout()\n",
|
||
"# plt.show()\n",
|
||
"\n",
|
||
"# plot_training_history(history.history)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 130,
|
||
"id": "df36e200",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# def token_level_accuracy(y_true, y_pred):\n",
|
||
"# total, correct = 0, 0\n",
|
||
"# for true_seq, pred_seq in zip(y_true, y_pred):\n",
|
||
"# for t, p in zip(true_seq, pred_seq):\n",
|
||
"# if t.sum() == 0:\n",
|
||
"# continue\n",
|
||
"# total += 1\n",
|
||
"# if t.argmax() == p.argmax():\n",
|
||
"# correct += 1\n",
|
||
"# return correct / total\n",
|
||
"\n",
|
||
"# def decode_predictions(pred, true, idx2tag):\n",
|
||
"# true_out, pred_out = [], []\n",
|
||
"# for pred_seq, true_seq in zip(pred, true):\n",
|
||
"# t_labels, p_labels = [], []\n",
|
||
"# for p_tok, t_tok in zip(pred_seq, true_seq):\n",
|
||
"# if t_tok.sum() == 0:\n",
|
||
"# continue\n",
|
||
"# t_labels.append(idx2tag[t_tok.argmax()])\n",
|
||
"# p_labels.append(idx2tag[p_tok.argmax()])\n",
|
||
"# true_out.append(t_labels)\n",
|
||
"# pred_out.append(p_labels)\n",
|
||
"# return true_out, pred_out\n",
|
||
"\n",
|
||
"# results = model.evaluate(X_test, {\"ner_output\": y_ner_test, \"srl_output\": y_srl_test}, verbose=0)\n",
|
||
"# for name, value in zip(model.metrics_names, results):\n",
|
||
"# print(f\"{name}: {value}\")\n",
|
||
"\n",
|
||
"# y_pred_ner, y_pred_srl = model.predict(X_test, verbose=0)\n",
|
||
"\n",
|
||
"# true_ner, pred_ner = decode_predictions(y_pred_ner, y_ner_test, idx2tag_ner)\n",
|
||
"# true_srl, pred_srl = decode_predictions(y_pred_srl, y_srl_test, idx2tag_srl)\n",
|
||
"\n",
|
||
"# acc_ner = token_level_accuracy(y_ner_test, y_pred_ner)\n",
|
||
"# acc_srl = token_level_accuracy(y_srl_test, y_pred_srl)\n",
|
||
"\n",
|
||
"# print(f\"NER Token Accuracy {acc_ner:.2%}\")\n",
|
||
"# print(f\"SRL Token Accuracy {acc_srl:.2%}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 131,
|
||
"id": "9127cce0",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# print(\"[NER] Classification Report:\")\n",
|
||
"# print(classification_report(true_ner, pred_ner, digits=2))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 132,
|
||
"id": "300897b8",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# print(\"SRL Classification Resport:\")\n",
|
||
"# print(classification_report(true_srl, pred_srl, digits=2))"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "myenv",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.10.16"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|