{
"cells": [
{
"cell_type": "code",
"execution_count": 19,
"id": "263af9e9",
"metadata": {},
"outputs": [],
"source": [
"\n",
"import pickle\n",
"import tensorflow as tf\n",
"from tensorflow.keras.models import Model\n",
"from tensorflow.keras.layers import Input, Embedding, Bidirectional, LSTM, TimeDistributed, Dense\n",
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
"from tensorflow.keras.utils import to_categorical\n",
"from sklearn.model_selection import train_test_split\n",
"from seqeval.metrics import classification_report\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "4fc87f1b",
"metadata": {},
"outputs": [],
"source": [
"data = []\n",
"with open(\"../dataset/dataset_ner_srl.tsv\", encoding=\"utf-8\") as f:\n",
" tokens, ner_labels, srl_labels = [], [], []\n",
" for line in f:\n",
" line = line.strip()\n",
" if not line:\n",
" if tokens:\n",
" data.append({\n",
" \"tokens\": tokens,\n",
" \"labels_ner\": ner_labels,\n",
" \"labels_srl\": srl_labels\n",
" })\n",
" tokens, ner_labels, srl_labels = [], [], []\n",
" else:\n",
" token, ner, srl = line.split(\"\\t\")\n",
" tokens.append(token)\n",
" ner_labels.append(ner)\n",
" srl_labels.append(srl)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "48553e6b",
"metadata": {},
"outputs": [],
"source": [
"\n",
"# 2. Preprocessing\n",
"sentences = [[tok.lower() for tok in item[\"tokens\"]] for item in data]\n",
"labels_ner = [item[\"labels_ner\"] for item in data]\n",
"labels_srl = [item[\"labels_srl\"] for item in data]\n",
"\n",
"words = sorted({w for s in sentences for w in s})\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",
"word2idx = {w: i + 2 for i, w in enumerate(words)}\n",
"word2idx[\"PAD\"], word2idx[\"UNK\"] = 0, 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()}\n",
"\n",
"X = [[word2idx.get(w, word2idx[\"UNK\"]) 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 = 50\n",
"X = pad_sequences(X, maxlen=maxlen, padding=\"post\", value=word2idx[\"PAD\"])\n",
"y_ner = pad_sequences(y_ner, maxlen=maxlen, padding=\"post\", value=tag2idx_ner[\"O\"])\n",
"y_srl = pad_sequences(y_srl, maxlen=maxlen, padding=\"post\", value=tag2idx_srl[\"O\"])\n",
"\n",
"y_ner = to_categorical(y_ner, num_classes=len(tag2idx_ner))\n",
"y_srl = to_categorical(y_srl, num_classes=len(tag2idx_srl))\n",
"\n",
"X_train, X_test, y_ner_train, y_ner_test, y_srl_train, y_srl_test = train_test_split(\n",
" X, y_ner, y_srl, test_size=0.2, random_state=42, shuffle=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "1b4a1c61",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Model: \"functional_2\"\n",
"\n"
],
"text/plain": [
"\u001b[1mModel: \"functional_2\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃ Connected to ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
"│ input_layer_2 │ (None, 50) │ 0 │ - │\n",
"│ (InputLayer) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_2 │ (None, 50, 64) │ 92,800 │ input_layer_2[0]… │\n",
"│ (Embedding) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ bidirectional_2 │ (None, 50, 128) │ 66,048 │ embedding_2[0][0] │\n",
"│ (Bidirectional) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ ner_output │ (None, 50, 25) │ 3,225 │ bidirectional_2[… │\n",
"│ (TimeDistributed) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ srl_output │ (None, 50, 31) │ 3,999 │ bidirectional_2[… │\n",
"│ (TimeDistributed) │ │ │ │\n",
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
"\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",
"│ input_layer_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
"│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ embedding_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m92,800\u001b[0m │ input_layer_2[\u001b[38;5;34m0\u001b[0m]… │\n",
"│ (\u001b[38;5;33mEmbedding\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ bidirectional_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m66,048\u001b[0m │ embedding_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBidirectional\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ ner_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m25\u001b[0m) │ \u001b[38;5;34m3,225\u001b[0m │ bidirectional_2[\u001b[38;5;34m…\u001b[0m │\n",
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
"│ srl_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m31\u001b[0m) │ \u001b[38;5;34m3,999\u001b[0m │ bidirectional_2[\u001b[38;5;34m…\u001b[0m │\n",
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Total params: 166,072 (648.72 KB)\n",
"\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m166,072\u001b[0m (648.72 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Trainable params: 166,072 (648.72 KB)\n",
"\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m166,072\u001b[0m (648.72 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" Non-trainable params: 0 (0.00 B)\n",
"\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": [
"\n",
"# 3. Model\n",
"input_layer = Input(shape=(maxlen,))\n",
"embedding_layer = Embedding(input_dim=len(word2idx), output_dim=64)(input_layer)\n",
"bilstm_layer = Bidirectional(LSTM(units=64, return_sequences=True))(embedding_layer)\n",
"\n",
"ner_output = TimeDistributed(Dense(len(tag2idx_ner), activation=\"softmax\"), name=\"ner_output\")(bilstm_layer)\n",
"srl_output = TimeDistributed(Dense(len(tag2idx_srl), activation=\"softmax\"), name=\"srl_output\")(bilstm_layer)\n",
"\n",
"model = Model(inputs=input_layer, outputs=[ner_output, srl_output])\n",
"model.compile(\n",
" optimizer=\"adam\",\n",
" loss={\n",
" \"ner_output\": \"categorical_crossentropy\",\n",
" \"srl_output\": \"categorical_crossentropy\",\n",
" },\n",
" metrics={\n",
" \"ner_output\": [tf.keras.metrics.CategoricalAccuracy(name=\"accuracy\")],\n",
" \"srl_output\": [tf.keras.metrics.CategoricalAccuracy(name=\"accuracy\")],\n",
" }\n",
")\n",
"\n",
"model.summary()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "f41d6012",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 14ms/step - loss: 2.2486 - ner_output_accuracy: 0.9123 - ner_output_loss: 0.9804 - srl_output_accuracy: 0.7926 - srl_output_loss: 1.2682 - val_loss: 0.7742 - val_ner_output_accuracy: 0.9400 - val_ner_output_loss: 0.2603 - val_srl_output_accuracy: 0.8402 - val_srl_output_loss: 0.5139\n",
"Epoch 2/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.6923 - ner_output_accuracy: 0.9402 - ner_output_loss: 0.2531 - srl_output_accuracy: 0.8617 - srl_output_loss: 0.4393 - val_loss: 0.7104 - val_ner_output_accuracy: 0.9400 - val_ner_output_loss: 0.2412 - val_srl_output_accuracy: 0.8593 - val_srl_output_loss: 0.4692\n",
"Epoch 3/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.5879 - ner_output_accuracy: 0.9419 - ner_output_loss: 0.2117 - srl_output_accuracy: 0.8888 - srl_output_loss: 0.3762 - val_loss: 0.6122 - val_ner_output_accuracy: 0.9423 - val_ner_output_loss: 0.2058 - val_srl_output_accuracy: 0.8839 - val_srl_output_loss: 0.4064\n",
"Epoch 4/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.4602 - ner_output_accuracy: 0.9512 - ner_output_loss: 0.1677 - srl_output_accuracy: 0.9173 - srl_output_loss: 0.2925 - val_loss: 0.5394 - val_ner_output_accuracy: 0.9552 - val_ner_output_loss: 0.1733 - val_srl_output_accuracy: 0.8986 - val_srl_output_loss: 0.3661\n",
"Epoch 5/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.3767 - ner_output_accuracy: 0.9629 - ner_output_loss: 0.1242 - srl_output_accuracy: 0.9273 - srl_output_loss: 0.2525 - val_loss: 0.4978 - val_ner_output_accuracy: 0.9625 - val_ner_output_loss: 0.1567 - val_srl_output_accuracy: 0.9052 - val_srl_output_loss: 0.3411\n",
"Epoch 6/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.3493 - ner_output_accuracy: 0.9664 - ner_output_loss: 0.1120 - srl_output_accuracy: 0.9309 - srl_output_loss: 0.2373 - val_loss: 0.4831 - val_ner_output_accuracy: 0.9655 - val_ner_output_loss: 0.1478 - val_srl_output_accuracy: 0.9052 - val_srl_output_loss: 0.3353\n",
"Epoch 7/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.2634 - ner_output_accuracy: 0.9743 - ner_output_loss: 0.0914 - srl_output_accuracy: 0.9533 - srl_output_loss: 0.1721 - val_loss: 0.4774 - val_ner_output_accuracy: 0.9659 - val_ner_output_loss: 0.1442 - val_srl_output_accuracy: 0.9123 - val_srl_output_loss: 0.3332\n",
"Epoch 8/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.2110 - ner_output_accuracy: 0.9801 - ner_output_loss: 0.0732 - srl_output_accuracy: 0.9630 - srl_output_loss: 0.1378 - val_loss: 0.4799 - val_ner_output_accuracy: 0.9670 - val_ner_output_loss: 0.1466 - val_srl_output_accuracy: 0.9134 - val_srl_output_loss: 0.3333\n",
"Epoch 9/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.1970 - ner_output_accuracy: 0.9848 - ner_output_loss: 0.0605 - srl_output_accuracy: 0.9630 - srl_output_loss: 0.1366 - val_loss: 0.4818 - val_ner_output_accuracy: 0.9684 - val_ner_output_loss: 0.1470 - val_srl_output_accuracy: 0.9150 - val_srl_output_loss: 0.3348\n",
"Epoch 10/10\n",
"\u001b[1m176/176\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - loss: 0.1772 - ner_output_accuracy: 0.9852 - ner_output_loss: 0.0620 - srl_output_accuracy: 0.9705 - srl_output_loss: 0.1152 - val_loss: 0.4976 - val_ner_output_accuracy: 0.9686 - val_ner_output_loss: 0.1515 - val_srl_output_accuracy: 0.9120 - val_srl_output_loss: 0.3461\n"
]
}
],
"source": [
"history = model.fit(\n",
" X_train,\n",
" {\"ner_output\": y_ner_train, \"srl_output\": y_srl_train},\n",
" validation_data=(X_test, {\"ner_output\": y_ner_test, \"srl_output\": y_srl_test}),\n",
" batch_size=2,\n",
" epochs=10,\n",
" verbose=1\n",
")\n",
"\n",
"# 5. Save artifacts\n",
"model.save(\"multi_task_lstm_ner_srl_model_tf.keras\")\n",
"with open(\"word2idx.pkl\", \"wb\") as f:\n",
" pickle.dump(word2idx, f)\n",
"with open(\"tag2idx_ner.pkl\", \"wb\") as f:\n",
" pickle.dump(tag2idx_ner, f)\n",
"with open(\"tag2idx_srl.pkl\", \"wb\") as f:\n",
" pickle.dump(tag2idx_srl, f)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "333745fd",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\n",
"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)\n"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "df36e200",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loss: 0.49759986996650696\n",
"compile_metrics: 0.15222841501235962\n",
"ner_output_loss: 0.3517407178878784\n",
"srl_output_loss: 0.9686364531517029\n",
"WARNING:tensorflow:5 out of the last 7 calls to .one_step_on_data_distributed at 0x7f1c38cdba30> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
"NER Token Accuracy 96.86%\n",
"SRL Token Accuracy 91.20%\n"
]
}
],
"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%}\")\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "9127cce0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[NER] Classification Report:\n",
" precision recall f1-score support\n",
"\n",
" DATE 0.57 0.24 0.33 17\n",
" EVENT 0.33 0.60 0.43 5\n",
" LOC 0.73 0.66 0.69 108\n",
" MIN 0.00 0.00 0.00 6\n",
" ORG 1.00 0.18 0.31 11\n",
" PER 0.40 0.15 0.22 13\n",
" QUANT 0.00 0.00 0.00 1\n",
" RES 0.00 0.00 0.00 3\n",
" TIME 0.22 0.17 0.19 12\n",
"\n",
" micro avg 0.65 0.48 0.55 176\n",
" macro avg 0.36 0.22 0.24 176\n",
"weighted avg 0.62 0.48 0.52 176\n",
"\n"
]
}
],
"source": [
"print(\"[NER] Classification Report:\")\n",
"print(classification_report(true_ner, pred_ner, digits=2))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "300897b8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"SRL Classification Resport:\n",
" precision recall f1-score support\n",
"\n",
" ADV 0.00 0.00 0.00 6\n",
" ARG1 0.00 0.00 0.00 7\n",
" ARG2 0.00 0.00 0.00 2\n",
" CAU 0.07 0.12 0.09 8\n",
" COM 0.00 0.00 0.00 1\n",
" DIS 0.00 0.00 0.00 2\n",
" FRQ 0.00 0.00 0.00 1\n",
" LOC 0.58 0.67 0.62 57\n",
" MNR 0.07 0.33 0.12 12\n",
" MOD 1.00 0.17 0.29 6\n",
" NEG 0.00 0.00 0.00 3\n",
" ORD 0.00 0.00 0.00 1\n",
" PRD 0.00 0.00 0.00 1\n",
" PRP 0.00 0.00 0.00 3\n",
" RG0 0.29 0.28 0.29 32\n",
" RG1 0.39 0.56 0.46 140\n",
" RG2 0.04 0.03 0.03 32\n",
" RG3 0.00 0.00 0.00 6\n",
" SRC 0.00 0.00 0.00 1\n",
" TMP 0.48 0.44 0.46 34\n",
" _ 0.72 0.56 0.63 103\n",
"\n",
" micro avg 0.40 0.45 0.43 458\n",
" macro avg 0.17 0.15 0.14 458\n",
"weighted avg 0.43 0.45 0.43 458\n",
"\n"
]
}
],
"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
}