diff --git a/cw/09_sequence_labeling_ODPOWIEDZI.ipynb b/cw/09_sequence_labeling_ODPOWIEDZI.ipynb
deleted file mode 100644
index bce57be..0000000
--- a/cw/09_sequence_labeling_ODPOWIEDZI.ipynb
+++ /dev/null
@@ -1,951 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "![Logo 1](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech1.jpg)\n",
- "
\n",
- "
Ekstrakcja informacji
\n",
- " 9. Sequence labeling [ćwiczenia]
\n",
- " Jakub Pokrywka (2021)
\n",
- "\n",
- "\n",
- "![Logo 2](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech2.jpg)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# Klasyfikacja wieloklasowa i sequence labelling"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np\n",
- "import gensim\n",
- "import torch\n",
- "import pandas as pd\n",
- "import seaborn as sns\n",
- "from sklearn.model_selection import train_test_split\n",
- "\n",
- "from datasets import load_dataset\n",
- "from torchtext.vocab import Vocab\n",
- "from collections import Counter\n",
- "\n",
- "from sklearn.datasets import fetch_20newsgroups\n",
- "# https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html\n",
- "\n",
- "from sklearn.feature_extraction.text import TfidfVectorizer\n",
- "from sklearn.metrics import accuracy_score"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Klasyfikacja"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Klasfikacja binarna- 2 klasy"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "CATEGORIES = ['soc.religion.christian', 'alt.atheism']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "newsgroups = fetch_20newsgroups(categories=CATEGORIES)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "X = newsgroups['data']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y = newsgroups['target']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y_names = newsgroups['target_names']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "X[0:1]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "Y_names"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "del CATEGORIES, newsgroups, X, Y, Y_names"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### klasyfikacja wieloklasowa"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "newsgroups_train_dev = fetch_20newsgroups(subset = 'train')\n",
- "newsgroups_test = fetch_20newsgroups(subset = 'test')"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "newsgroups_train_dev_text = newsgroups_train_dev['data']\n",
- "newsgroups_test_text = newsgroups_test['data']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y_train_dev = newsgroups_train_dev['target']\n",
- "Y_test = newsgroups_test['target']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "newsgroups_train_text, newsgroups_dev_text, Y_train, Y_dev = train_test_split(newsgroups_train_dev_text, Y_train_dev, random_state=42)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y_names = newsgroups_train_dev['target_names']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y_train_dev"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "Y_names"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Jaki baseline?**"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": false
- },
- "outputs": [],
- "source": [
- "pd.value_counts(Y_train)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "accuracy_score(Y_test, np.ones_like(Y_test) * 10)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "\n",
- "\n",
- "**Pytanie** - w jaki sposób stworzyć taki klasyfikator na podstawie tylko wiedzy z poprzednich ćwiczeń?"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Zadanie - stworzyć klasyfikator regresji logistycznej one vs rest na podstawie tfdif. TFIDF powinien mieć słownik o wielkości 10000\n",
- "\n",
- "https://scikit-learn.org/stable/modules/generated/sklearn.multiclass.OneVsRestClassifier.html\n",
- "https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html\n",
- "https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "from sklearn.multiclass import OneVsRestClassifier\n",
- "from sklearn.linear_model import LogisticRegression\n",
- "from sklearn.feature_extraction.text import TfidfVectorizer"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "FEAUTERES = 10_000"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "vectorizer = TfidfVectorizer(max_features=FEAUTERES)\n",
- "X_train = vectorizer.fit_transform(newsgroups_train_text)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "X_dev = vectorizer.transform(newsgroups_dev_text)\n",
- "X_test = vectorizer.transform(newsgroups_test_text)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "clf = OneVsRestClassifier(LogisticRegression()).fit(X_train, Y_train)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "clf.predict(X_train[0:1])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "clf.predict_proba(X_train[0:1])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "np.max(clf.predict_proba(X_train[0]))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "accuracy_score(clf.predict(X_train), Y_train)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "accuracy_score(clf.predict(X_dev), Y_dev)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "accuracy_score(clf.predict(X_test), Y_test)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Podejście softmax na tfidif"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "**Zadanie** Na podstawie poprzednich zajęć stworzyć sieć w pytorch bez warstw ukrytych, z jedną warstwą *output* z funkcją softmax (bez trenowania i ewaluacji sieci)\n",
- "\n",
- "Użyć https://pytorch.org/docs/stable/generated/torch.nn.Softmax.html?highlight=softmax"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "X_train"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "class NeuralNetworkModel(torch.nn.Module):\n",
- "\n",
- " def __init__(self,FEAUTERES, output_size):\n",
- " super(NeuralNetworkModel, self).__init__()\n",
- " self.fc1 = torch.nn.Linear(FEAUTERES,OUTPUT_SIZE)\n",
- " self.softmax = torch.nn.Softmax(dim=0)\n",
- " \n",
- "\n",
- " def forward(self, x):\n",
- " x = self.fc1(x)\n",
- " x = self.softmax(x)\n",
- " return x"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "OUTPUT_SIZE = len(Y_names)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "nn_model = NeuralNetworkModel(FEAUTERES, OUTPUT_SIZE)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "nn_model(torch.Tensor(X_train[0:3].astype(np.float32).todense()))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "BATCH_SIZE = 5"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "criterion = torch.nn.NLLLoss()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.2)\n",
- "#optimizer = torch.optim.Adam(nn_model.parameters())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def get_loss_acc(model, X_dataset, Y_dataset):\n",
- " loss_score = 0\n",
- " acc_score = 0\n",
- " items_total = 0\n",
- " model.eval()\n",
- " for i in range(0, Y_dataset.shape[0], BATCH_SIZE):\n",
- " X = X_dataset[i:i+BATCH_SIZE]\n",
- " X = torch.tensor(X.astype(np.float32).todense())\n",
- " Y = Y_dataset[i:i+BATCH_SIZE]\n",
- " Y = torch.tensor(Y)\n",
- " Y_predictions = model(X)\n",
- " acc_score += torch.sum(torch.argmax(Y_predictions,dim=1) == Y).item()\n",
- " items_total += Y.shape[0] \n",
- "\n",
- " loss = criterion(Y_predictions, Y)\n",
- "\n",
- " loss_score += loss.item() * Y.shape[0] \n",
- " return (loss_score / items_total), (acc_score / items_total)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "for epoch in range(5):\n",
- " loss_score = 0\n",
- " acc_score = 0\n",
- " items_total = 0\n",
- " nn_model.train()\n",
- " for i in range(0, Y_train.shape[0], BATCH_SIZE):\n",
- " X = X_train[i:i+BATCH_SIZE]\n",
- " X = torch.tensor(X.astype(np.float32).todense())\n",
- " Y = Y_train[i:i+BATCH_SIZE]\n",
- "\n",
- " Y = torch.tensor(Y)\n",
- " Y_predictions = nn_model(X)\n",
- " acc_score += torch.sum(torch.argmax(Y_predictions,dim=1) == Y).item()\n",
- " items_total += Y.shape[0] \n",
- "\n",
- " optimizer.zero_grad()\n",
- " loss = criterion(Y_predictions, Y)\n",
- " loss.backward()\n",
- " optimizer.step()\n",
- "\n",
- "\n",
- " loss_score += loss.item() * Y.shape[0]\n",
- "\n",
- " \n",
- " display(epoch)\n",
- " display(get_loss_acc(nn_model, X_train, Y_train))\n",
- " display(get_loss_acc(nn_model, X_dev, Y_dev))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "X.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "newsgroups_train_text"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Podejście softmax z embeddingami na przykładzie NER"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "# !pip install torchtext\n",
- "# !pip install datasets"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "https://www.aclweb.org/anthology/W03-0419.pdf"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": false
- },
- "outputs": [],
- "source": [
- "dataset = load_dataset(\"conll2003\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def build_vocab(dataset):\n",
- " counter = Counter()\n",
- " for document in dataset:\n",
- " counter.update(document)\n",
- " return Vocab(counter, specials=['', '', '', ''])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "vocab = build_vocab(dataset['train']['tokens'])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "dataset['train']['tokens']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "len(vocab.itos)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "vocab['on']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def data_process(dt):\n",
- " return [ torch.tensor([vocab['']] +[vocab[token] for token in document ] + [vocab['']], dtype = torch.long) for document in dt]\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "def labels_process(dt):\n",
- " return [ torch.tensor([0] + document + [0], dtype = torch.long) for document in dt]\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "train_tokens_ids = data_process(dataset['train']['tokens'])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "test_tokens_ids = data_process(dataset['test']['tokens'])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "train_labels = labels_process(dataset['train']['ner_tags'])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "test_labels = labels_process(dataset['test']['ner_tags'])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "train_tokens_ids[0]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "max([max(x) for x in dataset['train']['ner_tags'] ])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "class NERModel(torch.nn.Module):\n",
- "\n",
- " def __init__(self,):\n",
- " super(NERModel, self).__init__()\n",
- " self.emb = torch.nn.Embedding(23627,200)\n",
- " self.fc1 = torch.nn.Linear(600,9)\n",
- " #self.softmax = torch.nn.Softmax(dim=0)\n",
- " # nie trzeba, bo używamy https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html\n",
- " # jako kryterium\n",
- " \n",
- "\n",
- " def forward(self, x):\n",
- " x = self.emb(x)\n",
- " x = x.reshape(600) \n",
- " x = self.fc1(x)\n",
- " #x = self.softmax(x)\n",
- " return x"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "train_tokens_ids[0][1:4]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "ner_model = NERModel()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "ner_model(train_tokens_ids[0][1:4])"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "criterion = torch.nn.CrossEntropyLoss()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "optimizer = torch.optim.Adam(ner_model.parameters())"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "len(train_labels)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "for epoch in range(2):\n",
- " loss_score = 0\n",
- " acc_score = 0\n",
- " prec_score = 0\n",
- " selected_items = 0\n",
- " recall_score = 0\n",
- " relevant_items = 0\n",
- " items_total = 0\n",
- " nn_model.train()\n",
- " #for i in range(len(train_labels)):\n",
- " for i in range(100):\n",
- " for j in range(1, len(train_labels[i]) - 1):\n",
- " \n",
- " X = train_tokens_ids[i][j-1: j+2]\n",
- " Y = train_labels[i][j: j+1]\n",
- "\n",
- " Y_predictions = ner_model(X)\n",
- " \n",
- " \n",
- " acc_score += int(torch.argmax(Y_predictions) == Y)\n",
- " \n",
- " if torch.argmax(Y_predictions) != 0:\n",
- " selected_items +=1\n",
- " if torch.argmax(Y_predictions) != 0 and torch.argmax(Y_predictions) == Y.item():\n",
- " prec_score += 1\n",
- " \n",
- " if Y.item() != 0:\n",
- " relevant_items +=1\n",
- " if Y.item() != 0 and torch.argmax(Y_predictions) == Y.item():\n",
- " recall_score += 1\n",
- " \n",
- " items_total += 1\n",
- "\n",
- " \n",
- " optimizer.zero_grad()\n",
- " loss = criterion(Y_predictions.unsqueeze(0), Y)\n",
- " loss.backward()\n",
- " optimizer.step()\n",
- "\n",
- "\n",
- " loss_score += loss.item() \n",
- " \n",
- " precision = prec_score / selected_items\n",
- " recall = recall_score / relevant_items\n",
- " f1_score = (2*precision * recall) / (precision + recall)\n",
- " display('epoch: ', epoch)\n",
- " display('loss: ', loss_score / items_total)\n",
- " display('acc: ', acc_score / items_total)\n",
- " display('prec: ', precision)\n",
- " display('recall: : ', recall)\n",
- " display('f1: ', f1_score)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "loss_score = 0\n",
- "acc_score = 0\n",
- "prec_score = 0\n",
- "selected_items = 0\n",
- "recall_score = 0\n",
- "relevant_items = 0\n",
- "items_total = 0\n",
- "nn_model.eval()\n",
- "for i in range(100):\n",
- "#for i in range(len(test_labels)):\n",
- " for j in range(1, len(test_labels[i]) - 1):\n",
- "\n",
- " X = test_tokens_ids[i][j-1: j+2]\n",
- " Y = test_labels[i][j: j+1]\n",
- "\n",
- " Y_predictions = ner_model(X)\n",
- "\n",
- "\n",
- " acc_score += int(torch.argmax(Y_predictions) == Y)\n",
- "\n",
- " if torch.argmax(Y_predictions) != 0:\n",
- " selected_items +=1\n",
- " if torch.argmax(Y_predictions) != 0 and torch.argmax(Y_predictions) == Y.item():\n",
- " prec_score += 1\n",
- "\n",
- " if Y.item() != 0:\n",
- " relevant_items +=1\n",
- " if Y.item() != 0 and torch.argmax(Y_predictions) == Y.item():\n",
- " recall_score += 1\n",
- "\n",
- " items_total += 1\n",
- "\n",
- "\n",
- " loss = criterion(Y_predictions.unsqueeze(0), Y)\n",
- "\n",
- "\n",
- "\n",
- " loss_score += loss.item() \n",
- "\n",
- "precision = prec_score / selected_items\n",
- "recall = recall_score / relevant_items\n",
- "f1_score = (2*precision * recall) / (precision + recall)\n",
- "display('loss: ', loss_score / items_total)\n",
- "display('acc: ', acc_score / items_total)\n",
- "display('prec: ', precision)\n",
- "display('recall: : ', recall)\n",
- "display('f1: ', f1_score)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Zadanie domowe\n",
- "\n",
- "- sklonować repozytorium https://git.wmi.amu.edu.pl/kubapok/en-ner-conll-2003\n",
- "- stworzyć klasyfikator bazujący na sieci neuronowej feed forward w pytorchu (można bazować na tym jupyterze lub nie).\n",
- "- klasyfikator powinien obejmować dodatkowe cechy (np. długość wyrazu, czy wyraz zaczyna się od wielkiej litery, stemmming słowa, czy zawiera cyfrę)\n",
- "- stworzyć predykcje w plikach dev-0/out.tsv oraz test-A/out.tsv\n",
- "- wynik fscore sprawdzony za pomocą narzędzia geval (patrz poprzednie zadanie) powinien wynosić conajmniej 0.60\n",
- "- proszę umieścić predykcję oraz skrypty generujące (w postaci tekstowej a nie jupyter) w repo, a w MS TEAMS umieścić link do swojego repo\n",
- "termin 08.06, 80 punktów\n"
- ]
- }
- ],
- "metadata": {
- "author": "Jakub Pokrywka",
- "email": "kubapok@wmi.amu.edu.pl",
- "kernelspec": {
- "display_name": "Python 3",
- "language": "python",
- "name": "python3"
- },
- "lang": "pl",
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.8.3"
- },
- "subtitle": "9.Sequence labeling[ćwiczenia]",
- "title": "Ekstrakcja informacji",
- "year": "2021"
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}