{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"source": [
"\n",
"\n",
"
Ekstrakcja informacji
\n",
" 13. Transformery 2 [\u0107wiczenia]
\n",
" Jakub Pokrywka (2021)
\n",
"\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Wizualizacja atencji\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"https://github.com/jessevig/bertviz"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: bertviz in /home/kuba/anaconda3/lib/python3.8/site-packages (1.1.0)\n",
"Requirement already satisfied: boto3 in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (1.17.93)\n",
"Requirement already satisfied: requests in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (2.24.0)\n",
"Requirement already satisfied: torch>=1.0 in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (1.8.1)\n",
"Requirement already satisfied: sentencepiece in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (0.1.95)\n",
"Requirement already satisfied: tqdm in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (4.47.0)\n",
"Requirement already satisfied: transformers>=2.0 in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (4.2.2)\n",
"Requirement already satisfied: regex in /home/kuba/anaconda3/lib/python3.8/site-packages (from bertviz) (2020.6.8)\n",
"Requirement already satisfied: botocore<1.21.0,>=1.20.93 in /home/kuba/anaconda3/lib/python3.8/site-packages (from boto3->bertviz) (1.20.93)\n",
"Requirement already satisfied: jmespath<1.0.0,>=0.7.1 in /home/kuba/anaconda3/lib/python3.8/site-packages (from boto3->bertviz) (0.10.0)\n",
"Requirement already satisfied: s3transfer<0.5.0,>=0.4.0 in /home/kuba/anaconda3/lib/python3.8/site-packages (from boto3->bertviz) (0.4.2)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /home/kuba/anaconda3/lib/python3.8/site-packages (from requests->bertviz) (2020.6.20)\n",
"Requirement already satisfied: idna<3,>=2.5 in /home/kuba/anaconda3/lib/python3.8/site-packages (from requests->bertviz) (2.10)\n",
"Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /home/kuba/anaconda3/lib/python3.8/site-packages (from requests->bertviz) (1.25.9)\n",
"Requirement already satisfied: chardet<4,>=3.0.2 in /home/kuba/anaconda3/lib/python3.8/site-packages (from requests->bertviz) (3.0.4)\n",
"Requirement already satisfied: typing-extensions in /home/kuba/anaconda3/lib/python3.8/site-packages (from torch>=1.0->bertviz) (3.7.4.2)\n",
"Requirement already satisfied: numpy in /home/kuba/anaconda3/lib/python3.8/site-packages (from torch>=1.0->bertviz) (1.18.5)\n",
"Requirement already satisfied: sacremoses in /home/kuba/anaconda3/lib/python3.8/site-packages (from transformers>=2.0->bertviz) (0.0.43)\n",
"Requirement already satisfied: tokenizers==0.9.4 in /home/kuba/anaconda3/lib/python3.8/site-packages (from transformers>=2.0->bertviz) (0.9.4)\n",
"Requirement already satisfied: packaging in /home/kuba/anaconda3/lib/python3.8/site-packages (from transformers>=2.0->bertviz) (20.4)\n",
"Requirement already satisfied: filelock in /home/kuba/anaconda3/lib/python3.8/site-packages (from transformers>=2.0->bertviz) (3.0.12)\n",
"Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /home/kuba/anaconda3/lib/python3.8/site-packages (from botocore<1.21.0,>=1.20.93->boto3->bertviz) (2.8.1)\n",
"Requirement already satisfied: six in /home/kuba/anaconda3/lib/python3.8/site-packages (from sacremoses->transformers>=2.0->bertviz) (1.15.0)\n",
"Requirement already satisfied: joblib in /home/kuba/anaconda3/lib/python3.8/site-packages (from sacremoses->transformers>=2.0->bertviz) (0.16.0)\n",
"Requirement already satisfied: click in /home/kuba/anaconda3/lib/python3.8/site-packages (from sacremoses->transformers>=2.0->bertviz) (7.1.2)\n",
"Requirement already satisfied: pyparsing>=2.0.2 in /home/kuba/anaconda3/lib/python3.8/site-packages (from packaging->transformers>=2.0->bertviz) (2.4.7)\n"
]
}
],
"source": [
"!pip install bertviz"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoTokenizer, AutoModel\n",
"from bertviz import model_view, head_view"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"TEXT = \"This is a sample input sentence for a transformer model\""
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"MODEL = \"distilbert-base-uncased\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(MODEL)\n",
"model = AutoModel.from_pretrained(MODEL, output_attentions=True)\n",
"inputs = tokenizer.encode(TEXT, return_tensors='pt')\n",
"outputs = model(inputs)\n",
"attention = outputs[-1]\n",
"tokens = tokenizer.convert_ids_to_tokens(inputs[0]) \n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### SELF ATTENTION MODELS"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
""
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" \n",
" \n",
"
\n",
" Layer: \n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"
\n",
"
\n",
" Layer: \n",
" Attention: \n",
" \n",
"
\n",
"
\n",
"
\n",
" Attention: \n",
" \n",
"
\n",
"
\n",
"
\n",
" Layer: \n",
" Attention: \n",
" \n",
"
\n",
"