1660 lines
58 KiB
Plaintext
1660 lines
58 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "077b0f04",
|
||
"metadata": {
|
||
"origin_pos": 0
|
||
},
|
||
"source": [
|
||
"# 机器翻译与数据集\n",
|
||
":label:`sec_machine_translation`\n",
|
||
"\n",
|
||
"语言模型是自然语言处理的关键，\n",
|
||
"而*机器翻译*是语言模型最成功的基准测试。\n",
|
||
"因为机器翻译正是将输入序列转换成输出序列的\n",
|
||
"*序列转换模型*（sequence transduction）的核心问题。\n",
|
||
"序列转换模型在各类现代人工智能应用中发挥着至关重要的作用，\n",
|
||
"因此我们将其做为本章剩余部分和 :numref:`chap_attention`的重点。\n",
|
||
"为此，本节将介绍机器翻译问题及其后文需要使用的数据集。\n",
|
||
"\n",
|
||
"*机器翻译*（machine translation）指的是\n",
|
||
"将序列从一种语言自动翻译成另一种语言。\n",
|
||
"事实上，这个研究领域可以追溯到数字计算机发明后不久的20世纪40年代，\n",
|
||
"特别是在第二次世界大战中使用计算机破解语言编码。\n",
|
||
"几十年来，在使用神经网络进行端到端学习的兴起之前，\n",
|
||
"统计学方法在这一领域一直占据主导地位\n",
|
||
" :cite:`Brown.Cocke.Della-Pietra.ea.1988,Brown.Cocke.Della-Pietra.ea.1990`。\n",
|
||
"因为*统计机器翻译*（statistical machine translation）涉及了\n",
|
||
"翻译模型和语言模型等组成部分的统计分析，\n",
|
||
"因此基于神经网络的方法通常被称为\n",
|
||
"*神经机器翻译*（neural machine translation），\n",
|
||
"用于将两种翻译模型区分开来。\n",
|
||
"\n",
|
||
"本书的关注点是神经网络机器翻译方法，强调的是端到端的学习。\n",
|
||
"与 :numref:`sec_language_model`中的语料库\n",
|
||
"是单一语言的语言模型问题存在不同，\n",
|
||
"机器翻译的数据集是由源语言和目标语言的文本序列对组成的。\n",
|
||
"因此，我们需要一种完全不同的方法来预处理机器翻译数据集，\n",
|
||
"而不是复用语言模型的预处理程序。\n",
|
||
"下面，我们看一下如何将预处理后的数据加载到小批量中用于训练。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "38f128f5",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:28.568184Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:28.567577Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:30.535405Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:30.534582Z"
|
||
},
|
||
"origin_pos": 2,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os\n",
|
||
"import torch\n",
|
||
"from d2l import torch as d2l"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "4f0458ec",
|
||
"metadata": {
|
||
"origin_pos": 5
|
||
},
|
||
"source": [
|
||
"## [**下载和预处理数据集**]\n",
|
||
"\n",
|
||
"首先，下载一个由[Tatoeba项目的双语句子对](http://www.manythings.org/anki/)\n",
|
||
"组成的“英－法”数据集，数据集中的每一行都是制表符分隔的文本序列对，\n",
|
||
"序列对由英文文本序列和翻译后的法语文本序列组成。\n",
|
||
"请注意，每个文本序列可以是一个句子，\n",
|
||
"也可以是包含多个句子的一个段落。\n",
|
||
"在这个将英语翻译成法语的机器翻译问题中，\n",
|
||
"英语是*源语言*（source language），\n",
|
||
"法语是*目标语言*（target language）。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "b3461d76",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:30.539676Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:30.539042Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:30.809623Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:30.808727Z"
|
||
},
|
||
"origin_pos": 6,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Downloading ../data/fra-eng.zip from http://d2l-data.s3-accelerate.amazonaws.com/fra-eng.zip...\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Go.\tVa !\n",
|
||
"Hi.\tSalut !\n",
|
||
"Run!\tCours !\n",
|
||
"Run!\tCourez !\n",
|
||
"Who?\tQui ?\n",
|
||
"Wow!\tÇa alors !\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"d2l.DATA_HUB['fra-eng'] = (d2l.DATA_URL + 'fra-eng.zip',\n",
|
||
" '94646ad1522d915e7b0f9296181140edcf86a4f5')\n",
|
||
"\n",
|
||
"#@save\n",
|
||
"def read_data_nmt():\n",
|
||
" \"\"\"载入“英语－法语”数据集\"\"\"\n",
|
||
" data_dir = d2l.download_extract('fra-eng')\n",
|
||
" with open(os.path.join(data_dir, 'fra.txt'), 'r',\n",
|
||
" encoding='utf-8') as f:\n",
|
||
" return f.read()\n",
|
||
"\n",
|
||
"raw_text = read_data_nmt()\n",
|
||
"print(raw_text[:75])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "de8c081f",
|
||
"metadata": {
|
||
"origin_pos": 7
|
||
},
|
||
"source": [
|
||
"下载数据集后，原始文本数据需要经过[**几个预处理步骤**]。\n",
|
||
"例如，我们用空格代替*不间断空格*（non-breaking space），\n",
|
||
"使用小写字母替换大写字母，并在单词和标点符号之间插入空格。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "114c461d",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:30.813835Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:30.813273Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:36.581927Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:36.580959Z"
|
||
},
|
||
"origin_pos": 8,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"go .\tva !\n",
|
||
"hi .\tsalut !\n",
|
||
"run !\tcours !\n",
|
||
"run !\tcourez !\n",
|
||
"who ?\tqui ?\n",
|
||
"wow !\tça alors !\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"def preprocess_nmt(text):\n",
|
||
" \"\"\"预处理“英语－法语”数据集\"\"\"\n",
|
||
" def no_space(char, prev_char):\n",
|
||
" return char in set(',.!?') and prev_char != ' '\n",
|
||
"\n",
|
||
" # 使用空格替换不间断空格\n",
|
||
" # 使用小写字母替换大写字母\n",
|
||
" text = text.replace('\\u202f', ' ').replace('\\xa0', ' ').lower()\n",
|
||
" # 在单词和标点符号之间插入空格\n",
|
||
" out = [' ' + char if i > 0 and no_space(char, text[i - 1]) else char\n",
|
||
" for i, char in enumerate(text)]\n",
|
||
" return ''.join(out)\n",
|
||
"\n",
|
||
"text = preprocess_nmt(raw_text)\n",
|
||
"print(text[:80])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e4048187",
|
||
"metadata": {
|
||
"origin_pos": 9
|
||
},
|
||
"source": [
|
||
"## [**词元化**]\n",
|
||
"\n",
|
||
"与 :numref:`sec_language_model`中的字符级词元化不同，\n",
|
||
"在机器翻译中，我们更喜欢单词级词元化\n",
|
||
"（最先进的模型可能使用更高级的词元化技术）。\n",
|
||
"下面的`tokenize_nmt`函数对前`num_examples`个文本序列对进行词元，\n",
|
||
"其中每个词元要么是一个词，要么是一个标点符号。\n",
|
||
"此函数返回两个词元列表：`source`和`target`：\n",
|
||
"`source[i]`是源语言（这里是英语）第$i$个文本序列的词元列表，\n",
|
||
"`target[i]`是目标语言（这里是法语）第$i$个文本序列的词元列表。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "cc08d1a5",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:36.585962Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:36.585396Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.431130Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.430360Z"
|
||
},
|
||
"origin_pos": 10,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"([['go', '.'],\n",
|
||
" ['hi', '.'],\n",
|
||
" ['run', '!'],\n",
|
||
" ['run', '!'],\n",
|
||
" ['who', '?'],\n",
|
||
" ['wow', '!']],\n",
|
||
" [['va', '!'],\n",
|
||
" ['salut', '!'],\n",
|
||
" ['cours', '!'],\n",
|
||
" ['courez', '!'],\n",
|
||
" ['qui', '?'],\n",
|
||
" ['ça', 'alors', '!']])"
|
||
]
|
||
},
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"def tokenize_nmt(text, num_examples=None):\n",
|
||
" \"\"\"词元化“英语－法语”数据数据集\"\"\"\n",
|
||
" source, target = [], []\n",
|
||
" for i, line in enumerate(text.split('\\n')):\n",
|
||
" if num_examples and i > num_examples:\n",
|
||
" break\n",
|
||
" parts = line.split('\\t')\n",
|
||
" if len(parts) == 2:\n",
|
||
" source.append(parts[0].split(' '))\n",
|
||
" target.append(parts[1].split(' '))\n",
|
||
" return source, target\n",
|
||
"\n",
|
||
"source, target = tokenize_nmt(text)\n",
|
||
"source[:6], target[:6]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1d8ecec6",
|
||
"metadata": {
|
||
"origin_pos": 11
|
||
},
|
||
"source": [
|
||
"让我们[**绘制每个文本序列所包含的词元数量的直方图**]。\n",
|
||
"在这个简单的“英－法”数据集中，大多数文本序列的词元数量少于$20$个。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "118a08f5",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.436349Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.435794Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.726273Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.725467Z"
|
||
},
|
||
"origin_pos": 12,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/svg+xml": [
|
||
"<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
|
||
"<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
|
||
" \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
|
||
"<svg xmlns:xlink=\"http://www.w3.org/1999/xlink\" width=\"274.320356pt\" height=\"180.65625pt\" viewBox=\"0 0 274.320356 180.65625\" xmlns=\"http://www.w3.org/2000/svg\" version=\"1.1\">\n",
|
||
" <metadata>\n",
|
||
" <rdf:RDF xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:cc=\"http://creativecommons.org/ns#\" xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n",
|
||
" <cc:Work>\n",
|
||
" <dc:type rdf:resource=\"http://purl.org/dc/dcmitype/StillImage\"/>\n",
|
||
" <dc:date>2023-08-18T07:07:37.679341</dc:date>\n",
|
||
" <dc:format>image/svg+xml</dc:format>\n",
|
||
" <dc:creator>\n",
|
||
" <cc:Agent>\n",
|
||
" <dc:title>Matplotlib v3.5.1, https://matplotlib.org/</dc:title>\n",
|
||
" </cc:Agent>\n",
|
||
" </dc:creator>\n",
|
||
" </cc:Work>\n",
|
||
" </rdf:RDF>\n",
|
||
" </metadata>\n",
|
||
" <defs>\n",
|
||
" <style type=\"text/css\">*{stroke-linejoin: round; stroke-linecap: butt}</style>\n",
|
||
" </defs>\n",
|
||
" <g id=\"figure_1\">\n",
|
||
" <g id=\"patch_1\">\n",
|
||
" <path d=\"M 0 180.65625 \n",
|
||
"L 274.320356 180.65625 \n",
|
||
"L 274.320356 0 \n",
|
||
"L 0 0 \n",
|
||
"L 0 180.65625 \n",
|
||
"z\n",
|
||
"\" style=\"fill: none\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"axes_1\">\n",
|
||
" <g id=\"patch_2\">\n",
|
||
" <path d=\"M 66.053125 143.1 \n",
|
||
"L 261.353125 143.1 \n",
|
||
"L 261.353125 7.2 \n",
|
||
"L 66.053125 7.2 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_3\">\n",
|
||
" <path d=\"M 74.930398 143.1 \n",
|
||
"L 82.177151 143.1 \n",
|
||
"L 82.177151 13.671429 \n",
|
||
"L 74.930398 13.671429 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_4\">\n",
|
||
" <path d=\"M 93.047281 143.1 \n",
|
||
"L 100.294034 143.1 \n",
|
||
"L 100.294034 69.112838 \n",
|
||
"L 93.047281 69.112838 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_5\">\n",
|
||
" <path d=\"M 111.164164 143.1 \n",
|
||
"L 118.410917 143.1 \n",
|
||
"L 118.410917 138.560551 \n",
|
||
"L 111.164164 138.560551 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_6\">\n",
|
||
" <path d=\"M 129.281047 143.1 \n",
|
||
"L 136.5278 143.1 \n",
|
||
"L 136.5278 142.652168 \n",
|
||
"L 129.281047 142.652168 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_7\">\n",
|
||
" <path d=\"M 147.39793 143.1 \n",
|
||
"L 154.644683 143.1 \n",
|
||
"L 154.644683 143.045112 \n",
|
||
"L 147.39793 143.045112 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_8\">\n",
|
||
" <path d=\"M 165.514813 143.1 \n",
|
||
"L 172.761567 143.1 \n",
|
||
"L 172.761567 143.083783 \n",
|
||
"L 165.514813 143.083783 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_9\">\n",
|
||
" <path d=\"M 183.631696 143.1 \n",
|
||
"L 190.87845 143.1 \n",
|
||
"L 190.87845 143.092515 \n",
|
||
"L 183.631696 143.092515 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_10\">\n",
|
||
" <path d=\"M 201.74858 143.1 \n",
|
||
"L 208.995333 143.1 \n",
|
||
"L 208.995333 143.098753 \n",
|
||
"L 201.74858 143.098753 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_11\">\n",
|
||
" <path d=\"M 219.865463 143.1 \n",
|
||
"L 227.112216 143.1 \n",
|
||
"L 227.112216 143.097505 \n",
|
||
"L 219.865463 143.097505 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_12\">\n",
|
||
" <path d=\"M 237.982346 143.1 \n",
|
||
"L 245.229099 143.1 \n",
|
||
"L 245.229099 143.1 \n",
|
||
"L 237.982346 143.1 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_13\">\n",
|
||
" <path d=\"M 82.177151 143.1 \n",
|
||
"L 89.423904 143.1 \n",
|
||
"L 89.423904 26.397854 \n",
|
||
"L 82.177151 26.397854 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_14\">\n",
|
||
" <path d=\"M 100.294034 143.1 \n",
|
||
"L 107.540787 143.1 \n",
|
||
"L 107.540787 59.453878 \n",
|
||
"L 100.294034 59.453878 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_15\">\n",
|
||
" <path d=\"M 118.410917 143.1 \n",
|
||
"L 125.65767 143.1 \n",
|
||
"L 125.65767 136.044456 \n",
|
||
"L 118.410917 136.044456 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_16\">\n",
|
||
" <path d=\"M 136.5278 143.1 \n",
|
||
"L 143.774554 143.1 \n",
|
||
"L 143.774554 142.176891 \n",
|
||
"L 136.5278 142.176891 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_17\">\n",
|
||
" <path d=\"M 154.644683 143.1 \n",
|
||
"L 161.891437 143.1 \n",
|
||
"L 161.891437 142.993967 \n",
|
||
"L 154.644683 142.993967 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_18\">\n",
|
||
" <path d=\"M 172.761567 143.1 \n",
|
||
"L 180.00832 143.1 \n",
|
||
"L 180.00832 143.058834 \n",
|
||
"L 172.761567 143.058834 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_19\">\n",
|
||
" <path d=\"M 190.87845 143.1 \n",
|
||
"L 198.125203 143.1 \n",
|
||
"L 198.125203 143.097505 \n",
|
||
"L 190.87845 143.097505 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_20\">\n",
|
||
" <path d=\"M 208.995333 143.1 \n",
|
||
"L 216.242086 143.1 \n",
|
||
"L 216.242086 143.097505 \n",
|
||
"L 208.995333 143.097505 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_21\">\n",
|
||
" <path d=\"M 227.112216 143.1 \n",
|
||
"L 234.358969 143.1 \n",
|
||
"L 234.358969 143.097505 \n",
|
||
"L 227.112216 143.097505 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_22\">\n",
|
||
" <path d=\"M 245.229099 143.1 \n",
|
||
"L 252.475852 143.1 \n",
|
||
"L 252.475852 143.096258 \n",
|
||
"L 245.229099 143.096258 \n",
|
||
"z\n",
|
||
"\" clip-path=\"url(#p4f217efe07)\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_1\">\n",
|
||
" <g id=\"xtick_1\">\n",
|
||
" <g id=\"line2d_1\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"mfde7d55445\" d=\"M 0 0 \n",
|
||
"L 0 3.5 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mfde7d55445\" x=\"66.648394\" y=\"143.1\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_1\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(63.467144 157.698438)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-30\" d=\"M 2034 4250 \n",
|
||
"Q 1547 4250 1301 3770 \n",
|
||
"Q 1056 3291 1056 2328 \n",
|
||
"Q 1056 1369 1301 889 \n",
|
||
"Q 1547 409 2034 409 \n",
|
||
"Q 2525 409 2770 889 \n",
|
||
"Q 3016 1369 3016 2328 \n",
|
||
"Q 3016 3291 2770 3770 \n",
|
||
"Q 2525 4250 2034 4250 \n",
|
||
"z\n",
|
||
"M 2034 4750 \n",
|
||
"Q 2819 4750 3233 4129 \n",
|
||
"Q 3647 3509 3647 2328 \n",
|
||
"Q 3647 1150 3233 529 \n",
|
||
"Q 2819 -91 2034 -91 \n",
|
||
"Q 1250 -91 836 529 \n",
|
||
"Q 422 1150 422 2328 \n",
|
||
"Q 422 3509 836 4129 \n",
|
||
"Q 1250 4750 2034 4750 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_2\">\n",
|
||
" <g id=\"line2d_2\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mfde7d55445\" x=\"131.351548\" y=\"143.1\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_2\">\n",
|
||
" <!-- 20 -->\n",
|
||
" <g transform=\"translate(124.989048 157.698438)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-32\" d=\"M 1228 531 \n",
|
||
"L 3431 531 \n",
|
||
"L 3431 0 \n",
|
||
"L 469 0 \n",
|
||
"L 469 531 \n",
|
||
"Q 828 903 1448 1529 \n",
|
||
"Q 2069 2156 2228 2338 \n",
|
||
"Q 2531 2678 2651 2914 \n",
|
||
"Q 2772 3150 2772 3378 \n",
|
||
"Q 2772 3750 2511 3984 \n",
|
||
"Q 2250 4219 1831 4219 \n",
|
||
"Q 1534 4219 1204 4116 \n",
|
||
"Q 875 4013 500 3803 \n",
|
||
"L 500 4441 \n",
|
||
"Q 881 4594 1212 4672 \n",
|
||
"Q 1544 4750 1819 4750 \n",
|
||
"Q 2544 4750 2975 4387 \n",
|
||
"Q 3406 4025 3406 3419 \n",
|
||
"Q 3406 3131 3298 2873 \n",
|
||
"Q 3191 2616 2906 2266 \n",
|
||
"Q 2828 2175 2409 1742 \n",
|
||
"Q 1991 1309 1228 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_3\">\n",
|
||
" <g id=\"line2d_3\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mfde7d55445\" x=\"196.054702\" y=\"143.1\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_3\">\n",
|
||
" <!-- 40 -->\n",
|
||
" <g transform=\"translate(189.692202 157.698438)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-34\" d=\"M 2419 4116 \n",
|
||
"L 825 1625 \n",
|
||
"L 2419 1625 \n",
|
||
"L 2419 4116 \n",
|
||
"z\n",
|
||
"M 2253 4666 \n",
|
||
"L 3047 4666 \n",
|
||
"L 3047 1625 \n",
|
||
"L 3713 1625 \n",
|
||
"L 3713 1100 \n",
|
||
"L 3047 1100 \n",
|
||
"L 3047 0 \n",
|
||
"L 2419 0 \n",
|
||
"L 2419 1100 \n",
|
||
"L 313 1100 \n",
|
||
"L 313 1709 \n",
|
||
"L 2253 4666 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"xtick_4\">\n",
|
||
" <g id=\"line2d_4\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#mfde7d55445\" x=\"260.757856\" y=\"143.1\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_4\">\n",
|
||
" <!-- 60 -->\n",
|
||
" <g transform=\"translate(254.395356 157.698438)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-36\" d=\"M 2113 2584 \n",
|
||
"Q 1688 2584 1439 2293 \n",
|
||
"Q 1191 2003 1191 1497 \n",
|
||
"Q 1191 994 1439 701 \n",
|
||
"Q 1688 409 2113 409 \n",
|
||
"Q 2538 409 2786 701 \n",
|
||
"Q 3034 994 3034 1497 \n",
|
||
"Q 3034 2003 2786 2293 \n",
|
||
"Q 2538 2584 2113 2584 \n",
|
||
"z\n",
|
||
"M 3366 4563 \n",
|
||
"L 3366 3988 \n",
|
||
"Q 3128 4100 2886 4159 \n",
|
||
"Q 2644 4219 2406 4219 \n",
|
||
"Q 1781 4219 1451 3797 \n",
|
||
"Q 1122 3375 1075 2522 \n",
|
||
"Q 1259 2794 1537 2939 \n",
|
||
"Q 1816 3084 2150 3084 \n",
|
||
"Q 2853 3084 3261 2657 \n",
|
||
"Q 3669 2231 3669 1497 \n",
|
||
"Q 3669 778 3244 343 \n",
|
||
"Q 2819 -91 2113 -91 \n",
|
||
"Q 1303 -91 875 529 \n",
|
||
"Q 447 1150 447 2328 \n",
|
||
"Q 447 3434 972 4092 \n",
|
||
"Q 1497 4750 2381 4750 \n",
|
||
"Q 2619 4750 2861 4703 \n",
|
||
"Q 3103 4656 3366 4563 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_5\">\n",
|
||
" <!-- # tokens per sequence -->\n",
|
||
" <g transform=\"translate(105.760937 171.376563)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-23\" d=\"M 3272 2816 \n",
|
||
"L 2363 2816 \n",
|
||
"L 2100 1772 \n",
|
||
"L 3016 1772 \n",
|
||
"L 3272 2816 \n",
|
||
"z\n",
|
||
"M 2803 4594 \n",
|
||
"L 2478 3297 \n",
|
||
"L 3391 3297 \n",
|
||
"L 3719 4594 \n",
|
||
"L 4219 4594 \n",
|
||
"L 3897 3297 \n",
|
||
"L 4872 3297 \n",
|
||
"L 4872 2816 \n",
|
||
"L 3775 2816 \n",
|
||
"L 3519 1772 \n",
|
||
"L 4513 1772 \n",
|
||
"L 4513 1294 \n",
|
||
"L 3397 1294 \n",
|
||
"L 3072 0 \n",
|
||
"L 2572 0 \n",
|
||
"L 2894 1294 \n",
|
||
"L 1978 1294 \n",
|
||
"L 1656 0 \n",
|
||
"L 1153 0 \n",
|
||
"L 1478 1294 \n",
|
||
"L 494 1294 \n",
|
||
"L 494 1772 \n",
|
||
"L 1594 1772 \n",
|
||
"L 1856 2816 \n",
|
||
"L 850 2816 \n",
|
||
"L 850 3297 \n",
|
||
"L 1978 3297 \n",
|
||
"L 2297 4594 \n",
|
||
"L 2803 4594 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-20\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-74\" d=\"M 1172 4494 \n",
|
||
"L 1172 3500 \n",
|
||
"L 2356 3500 \n",
|
||
"L 2356 3053 \n",
|
||
"L 1172 3053 \n",
|
||
"L 1172 1153 \n",
|
||
"Q 1172 725 1289 603 \n",
|
||
"Q 1406 481 1766 481 \n",
|
||
"L 2356 481 \n",
|
||
"L 2356 0 \n",
|
||
"L 1766 0 \n",
|
||
"Q 1100 0 847 248 \n",
|
||
"Q 594 497 594 1153 \n",
|
||
"L 594 3053 \n",
|
||
"L 172 3053 \n",
|
||
"L 172 3500 \n",
|
||
"L 594 3500 \n",
|
||
"L 594 4494 \n",
|
||
"L 1172 4494 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6f\" d=\"M 1959 3097 \n",
|
||
"Q 1497 3097 1228 2736 \n",
|
||
"Q 959 2375 959 1747 \n",
|
||
"Q 959 1119 1226 758 \n",
|
||
"Q 1494 397 1959 397 \n",
|
||
"Q 2419 397 2687 759 \n",
|
||
"Q 2956 1122 2956 1747 \n",
|
||
"Q 2956 2369 2687 2733 \n",
|
||
"Q 2419 3097 1959 3097 \n",
|
||
"z\n",
|
||
"M 1959 3584 \n",
|
||
"Q 2709 3584 3137 3096 \n",
|
||
"Q 3566 2609 3566 1747 \n",
|
||
"Q 3566 888 3137 398 \n",
|
||
"Q 2709 -91 1959 -91 \n",
|
||
"Q 1206 -91 779 398 \n",
|
||
"Q 353 888 353 1747 \n",
|
||
"Q 353 2609 779 3096 \n",
|
||
"Q 1206 3584 1959 3584 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6b\" d=\"M 581 4863 \n",
|
||
"L 1159 4863 \n",
|
||
"L 1159 1991 \n",
|
||
"L 2875 3500 \n",
|
||
"L 3609 3500 \n",
|
||
"L 1753 1863 \n",
|
||
"L 3688 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 1159 1709 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 4863 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-65\" d=\"M 3597 1894 \n",
|
||
"L 3597 1613 \n",
|
||
"L 953 1613 \n",
|
||
"Q 991 1019 1311 708 \n",
|
||
"Q 1631 397 2203 397 \n",
|
||
"Q 2534 397 2845 478 \n",
|
||
"Q 3156 559 3463 722 \n",
|
||
"L 3463 178 \n",
|
||
"Q 3153 47 2828 -22 \n",
|
||
"Q 2503 -91 2169 -91 \n",
|
||
"Q 1331 -91 842 396 \n",
|
||
"Q 353 884 353 1716 \n",
|
||
"Q 353 2575 817 3079 \n",
|
||
"Q 1281 3584 2069 3584 \n",
|
||
"Q 2775 3584 3186 3129 \n",
|
||
"Q 3597 2675 3597 1894 \n",
|
||
"z\n",
|
||
"M 3022 2063 \n",
|
||
"Q 3016 2534 2758 2815 \n",
|
||
"Q 2500 3097 2075 3097 \n",
|
||
"Q 1594 3097 1305 2825 \n",
|
||
"Q 1016 2553 972 2059 \n",
|
||
"L 3022 2063 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-6e\" d=\"M 3513 2113 \n",
|
||
"L 3513 0 \n",
|
||
"L 2938 0 \n",
|
||
"L 2938 2094 \n",
|
||
"Q 2938 2591 2744 2837 \n",
|
||
"Q 2550 3084 2163 3084 \n",
|
||
"Q 1697 3084 1428 2787 \n",
|
||
"Q 1159 2491 1159 1978 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1366 3272 1645 3428 \n",
|
||
"Q 1925 3584 2291 3584 \n",
|
||
"Q 2894 3584 3203 3211 \n",
|
||
"Q 3513 2838 3513 2113 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-73\" d=\"M 2834 3397 \n",
|
||
"L 2834 2853 \n",
|
||
"Q 2591 2978 2328 3040 \n",
|
||
"Q 2066 3103 1784 3103 \n",
|
||
"Q 1356 3103 1142 2972 \n",
|
||
"Q 928 2841 928 2578 \n",
|
||
"Q 928 2378 1081 2264 \n",
|
||
"Q 1234 2150 1697 2047 \n",
|
||
"L 1894 2003 \n",
|
||
"Q 2506 1872 2764 1633 \n",
|
||
"Q 3022 1394 3022 966 \n",
|
||
"Q 3022 478 2636 193 \n",
|
||
"Q 2250 -91 1575 -91 \n",
|
||
"Q 1294 -91 989 -36 \n",
|
||
"Q 684 19 347 128 \n",
|
||
"L 347 722 \n",
|
||
"Q 666 556 975 473 \n",
|
||
"Q 1284 391 1588 391 \n",
|
||
"Q 1994 391 2212 530 \n",
|
||
"Q 2431 669 2431 922 \n",
|
||
"Q 2431 1156 2273 1281 \n",
|
||
"Q 2116 1406 1581 1522 \n",
|
||
"L 1381 1569 \n",
|
||
"Q 847 1681 609 1914 \n",
|
||
"Q 372 2147 372 2553 \n",
|
||
"Q 372 3047 722 3315 \n",
|
||
"Q 1072 3584 1716 3584 \n",
|
||
"Q 2034 3584 2315 3537 \n",
|
||
"Q 2597 3491 2834 3397 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-70\" d=\"M 1159 525 \n",
|
||
"L 1159 -1331 \n",
|
||
"L 581 -1331 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2969 \n",
|
||
"Q 1341 3281 1617 3432 \n",
|
||
"Q 1894 3584 2278 3584 \n",
|
||
"Q 2916 3584 3314 3078 \n",
|
||
"Q 3713 2572 3713 1747 \n",
|
||
"Q 3713 922 3314 415 \n",
|
||
"Q 2916 -91 2278 -91 \n",
|
||
"Q 1894 -91 1617 61 \n",
|
||
"Q 1341 213 1159 525 \n",
|
||
"z\n",
|
||
"M 3116 1747 \n",
|
||
"Q 3116 2381 2855 2742 \n",
|
||
"Q 2594 3103 2138 3103 \n",
|
||
"Q 1681 3103 1420 2742 \n",
|
||
"Q 1159 2381 1159 1747 \n",
|
||
"Q 1159 1113 1420 752 \n",
|
||
"Q 1681 391 2138 391 \n",
|
||
"Q 2594 391 2855 752 \n",
|
||
"Q 3116 1113 3116 1747 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-72\" d=\"M 2631 2963 \n",
|
||
"Q 2534 3019 2420 3045 \n",
|
||
"Q 2306 3072 2169 3072 \n",
|
||
"Q 1681 3072 1420 2755 \n",
|
||
"Q 1159 2438 1159 1844 \n",
|
||
"L 1159 0 \n",
|
||
"L 581 0 \n",
|
||
"L 581 3500 \n",
|
||
"L 1159 3500 \n",
|
||
"L 1159 2956 \n",
|
||
"Q 1341 3275 1631 3429 \n",
|
||
"Q 1922 3584 2338 3584 \n",
|
||
"Q 2397 3584 2469 3576 \n",
|
||
"Q 2541 3569 2628 3553 \n",
|
||
"L 2631 2963 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-71\" d=\"M 947 1747 \n",
|
||
"Q 947 1113 1208 752 \n",
|
||
"Q 1469 391 1925 391 \n",
|
||
"Q 2381 391 2643 752 \n",
|
||
"Q 2906 1113 2906 1747 \n",
|
||
"Q 2906 2381 2643 2742 \n",
|
||
"Q 2381 3103 1925 3103 \n",
|
||
"Q 1469 3103 1208 2742 \n",
|
||
"Q 947 2381 947 1747 \n",
|
||
"z\n",
|
||
"M 2906 525 \n",
|
||
"Q 2725 213 2448 61 \n",
|
||
"Q 2172 -91 1784 -91 \n",
|
||
"Q 1150 -91 751 415 \n",
|
||
"Q 353 922 353 1747 \n",
|
||
"Q 353 2572 751 3078 \n",
|
||
"Q 1150 3584 1784 3584 \n",
|
||
"Q 2172 3584 2448 3432 \n",
|
||
"Q 2725 3281 2906 2969 \n",
|
||
"L 2906 3500 \n",
|
||
"L 3481 3500 \n",
|
||
"L 3481 -1331 \n",
|
||
"L 2906 -1331 \n",
|
||
"L 2906 525 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-75\" d=\"M 544 1381 \n",
|
||
"L 544 3500 \n",
|
||
"L 1119 3500 \n",
|
||
"L 1119 1403 \n",
|
||
"Q 1119 906 1312 657 \n",
|
||
"Q 1506 409 1894 409 \n",
|
||
"Q 2359 409 2629 706 \n",
|
||
"Q 2900 1003 2900 1516 \n",
|
||
"L 2900 3500 \n",
|
||
"L 3475 3500 \n",
|
||
"L 3475 0 \n",
|
||
"L 2900 0 \n",
|
||
"L 2900 538 \n",
|
||
"Q 2691 219 2414 64 \n",
|
||
"Q 2138 -91 1772 -91 \n",
|
||
"Q 1169 -91 856 284 \n",
|
||
"Q 544 659 544 1381 \n",
|
||
"z\n",
|
||
"M 1991 3584 \n",
|
||
"L 1991 3584 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-63\" d=\"M 3122 3366 \n",
|
||
"L 3122 2828 \n",
|
||
"Q 2878 2963 2633 3030 \n",
|
||
"Q 2388 3097 2138 3097 \n",
|
||
"Q 1578 3097 1268 2742 \n",
|
||
"Q 959 2388 959 1747 \n",
|
||
"Q 959 1106 1268 751 \n",
|
||
"Q 1578 397 2138 397 \n",
|
||
"Q 2388 397 2633 464 \n",
|
||
"Q 2878 531 3122 666 \n",
|
||
"L 3122 134 \n",
|
||
"Q 2881 22 2623 -34 \n",
|
||
"Q 2366 -91 2075 -91 \n",
|
||
"Q 1284 -91 818 406 \n",
|
||
"Q 353 903 353 1747 \n",
|
||
"Q 353 2603 823 3093 \n",
|
||
"Q 1294 3584 2113 3584 \n",
|
||
"Q 2378 3584 2631 3529 \n",
|
||
"Q 2884 3475 3122 3366 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-23\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"83.789062\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"115.576172\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"154.785156\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6b\" x=\"215.966797\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"270.251953\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6e\" x=\"331.775391\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"395.154297\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"447.253906\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-70\" x=\"479.041016\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"542.517578\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"604.041016\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-20\" x=\"645.154297\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\" x=\"676.941406\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"729.041016\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-71\" x=\"790.564453\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-75\" x=\"854.041016\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"917.419922\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6e\" x=\"978.943359\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\" x=\"1042.322266\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"1097.302734\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"matplotlib.axis_2\">\n",
|
||
" <g id=\"ytick_1\">\n",
|
||
" <g id=\"line2d_5\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"m9adbfb286a\" d=\"M 0 0 \n",
|
||
"L -3.5 0 \n",
|
||
"\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </defs>\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"143.1\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_6\">\n",
|
||
" <!-- 0 -->\n",
|
||
" <g transform=\"translate(52.690625 146.899219)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_2\">\n",
|
||
" <g id=\"line2d_6\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"118.151116\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_7\">\n",
|
||
" <!-- 20000 -->\n",
|
||
" <g transform=\"translate(27.240625 121.950335)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-32\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"190.869141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"254.492188\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_3\">\n",
|
||
" <g id=\"line2d_7\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"93.202233\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_8\">\n",
|
||
" <!-- 40000 -->\n",
|
||
" <g transform=\"translate(27.240625 97.001451)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-34\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"190.869141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"254.492188\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_4\">\n",
|
||
" <g id=\"line2d_8\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"68.253349\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_9\">\n",
|
||
" <!-- 60000 -->\n",
|
||
" <g transform=\"translate(27.240625 72.052568)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-36\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"190.869141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"254.492188\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_5\">\n",
|
||
" <g id=\"line2d_9\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"43.304465\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_10\">\n",
|
||
" <!-- 80000 -->\n",
|
||
" <g transform=\"translate(27.240625 47.103684)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-38\" d=\"M 2034 2216 \n",
|
||
"Q 1584 2216 1326 1975 \n",
|
||
"Q 1069 1734 1069 1313 \n",
|
||
"Q 1069 891 1326 650 \n",
|
||
"Q 1584 409 2034 409 \n",
|
||
"Q 2484 409 2743 651 \n",
|
||
"Q 3003 894 3003 1313 \n",
|
||
"Q 3003 1734 2745 1975 \n",
|
||
"Q 2488 2216 2034 2216 \n",
|
||
"z\n",
|
||
"M 1403 2484 \n",
|
||
"Q 997 2584 770 2862 \n",
|
||
"Q 544 3141 544 3541 \n",
|
||
"Q 544 4100 942 4425 \n",
|
||
"Q 1341 4750 2034 4750 \n",
|
||
"Q 2731 4750 3128 4425 \n",
|
||
"Q 3525 4100 3525 3541 \n",
|
||
"Q 3525 3141 3298 2862 \n",
|
||
"Q 3072 2584 2669 2484 \n",
|
||
"Q 3125 2378 3379 2068 \n",
|
||
"Q 3634 1759 3634 1313 \n",
|
||
"Q 3634 634 3220 271 \n",
|
||
"Q 2806 -91 2034 -91 \n",
|
||
"Q 1263 -91 848 271 \n",
|
||
"Q 434 634 434 1313 \n",
|
||
"Q 434 1759 690 2068 \n",
|
||
"Q 947 2378 1403 2484 \n",
|
||
"z\n",
|
||
"M 1172 3481 \n",
|
||
"Q 1172 3119 1398 2916 \n",
|
||
"Q 1625 2713 2034 2713 \n",
|
||
"Q 2441 2713 2670 2916 \n",
|
||
"Q 2900 3119 2900 3481 \n",
|
||
"Q 2900 3844 2670 4047 \n",
|
||
"Q 2441 4250 2034 4250 \n",
|
||
"Q 1625 4250 1398 4047 \n",
|
||
"Q 1172 3844 1172 3481 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-38\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"190.869141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"254.492188\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"ytick_6\">\n",
|
||
" <g id=\"line2d_10\">\n",
|
||
" <g>\n",
|
||
" <use xlink:href=\"#m9adbfb286a\" x=\"66.053125\" y=\"18.355581\" style=\"stroke: #000000; stroke-width: 0.8\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_11\">\n",
|
||
" <!-- 100000 -->\n",
|
||
" <g transform=\"translate(20.878125 22.1548)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-31\" d=\"M 794 531 \n",
|
||
"L 1825 531 \n",
|
||
"L 1825 4091 \n",
|
||
"L 703 3866 \n",
|
||
"L 703 4441 \n",
|
||
"L 1819 4666 \n",
|
||
"L 2450 4666 \n",
|
||
"L 2450 531 \n",
|
||
"L 3481 531 \n",
|
||
"L 3481 0 \n",
|
||
"L 794 0 \n",
|
||
"L 794 531 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-31\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"63.623047\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"127.246094\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"190.869141\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"254.492188\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-30\" x=\"318.115234\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_12\">\n",
|
||
" <!-- count -->\n",
|
||
" <g transform=\"translate(14.798438 89.25625)rotate(-90)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"54.980469\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-75\" x=\"116.162109\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6e\" x=\"179.541016\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"242.919922\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_23\">\n",
|
||
" <path d=\"M 66.053125 143.1 \n",
|
||
"L 66.053125 7.2 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_24\">\n",
|
||
" <path d=\"M 261.353125 143.1 \n",
|
||
"L 261.353125 7.2 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_25\">\n",
|
||
" <path d=\"M 66.053125 143.1 \n",
|
||
"L 261.353125 143.1 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_26\">\n",
|
||
" <path d=\"M 66.053125 7.2 \n",
|
||
"L 261.353125 7.2 \n",
|
||
"\" style=\"fill: none; stroke: #000000; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"legend_1\">\n",
|
||
" <g id=\"patch_27\">\n",
|
||
" <path d=\"M 189.15 44.55625 \n",
|
||
"L 254.353125 44.55625 \n",
|
||
"Q 256.353125 44.55625 256.353125 42.55625 \n",
|
||
"L 256.353125 14.2 \n",
|
||
"Q 256.353125 12.2 254.353125 12.2 \n",
|
||
"L 189.15 12.2 \n",
|
||
"Q 187.15 12.2 187.15 14.2 \n",
|
||
"L 187.15 42.55625 \n",
|
||
"Q 187.15 44.55625 189.15 44.55625 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #ffffff; opacity: 0.8; stroke: #cccccc; stroke-linejoin: miter\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_28\">\n",
|
||
" <path d=\"M 191.15 23.798437 \n",
|
||
"L 211.15 23.798437 \n",
|
||
"L 211.15 16.798437 \n",
|
||
"L 191.15 16.798437 \n",
|
||
"z\n",
|
||
"\" style=\"fill: #1f77b4\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_13\">\n",
|
||
" <!-- source -->\n",
|
||
" <g transform=\"translate(219.15 23.798437)scale(0.1 -0.1)\">\n",
|
||
" <use xlink:href=\"#DejaVuSans-73\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-6f\" x=\"52.099609\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-75\" x=\"113.28125\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"176.660156\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-63\" x=\"215.523438\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"270.503906\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <g id=\"patch_29\">\n",
|
||
" <path d=\"M 191.15 38.476562 \n",
|
||
"L 211.15 38.476562 \n",
|
||
"L 211.15 31.476562 \n",
|
||
"L 191.15 31.476562 \n",
|
||
"z\n",
|
||
"\" style=\"fill: url(#h446a4b1fc9)\"/>\n",
|
||
" </g>\n",
|
||
" <g id=\"text_14\">\n",
|
||
" <!-- target -->\n",
|
||
" <g transform=\"translate(219.15 38.476562)scale(0.1 -0.1)\">\n",
|
||
" <defs>\n",
|
||
" <path id=\"DejaVuSans-61\" d=\"M 2194 1759 \n",
|
||
"Q 1497 1759 1228 1600 \n",
|
||
"Q 959 1441 959 1056 \n",
|
||
"Q 959 750 1161 570 \n",
|
||
"Q 1363 391 1709 391 \n",
|
||
"Q 2188 391 2477 730 \n",
|
||
"Q 2766 1069 2766 1631 \n",
|
||
"L 2766 1759 \n",
|
||
"L 2194 1759 \n",
|
||
"z\n",
|
||
"M 3341 1997 \n",
|
||
"L 3341 0 \n",
|
||
"L 2766 0 \n",
|
||
"L 2766 531 \n",
|
||
"Q 2569 213 2275 61 \n",
|
||
"Q 1981 -91 1556 -91 \n",
|
||
"Q 1019 -91 701 211 \n",
|
||
"Q 384 513 384 1019 \n",
|
||
"Q 384 1609 779 1909 \n",
|
||
"Q 1175 2209 1959 2209 \n",
|
||
"L 2766 2209 \n",
|
||
"L 2766 2266 \n",
|
||
"Q 2766 2663 2505 2880 \n",
|
||
"Q 2244 3097 1772 3097 \n",
|
||
"Q 1472 3097 1187 3025 \n",
|
||
"Q 903 2953 641 2809 \n",
|
||
"L 641 3341 \n",
|
||
"Q 956 3463 1253 3523 \n",
|
||
"Q 1550 3584 1831 3584 \n",
|
||
"Q 2591 3584 2966 3190 \n",
|
||
"Q 3341 2797 3341 1997 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" <path id=\"DejaVuSans-67\" d=\"M 2906 1791 \n",
|
||
"Q 2906 2416 2648 2759 \n",
|
||
"Q 2391 3103 1925 3103 \n",
|
||
"Q 1463 3103 1205 2759 \n",
|
||
"Q 947 2416 947 1791 \n",
|
||
"Q 947 1169 1205 825 \n",
|
||
"Q 1463 481 1925 481 \n",
|
||
"Q 2391 481 2648 825 \n",
|
||
"Q 2906 1169 2906 1791 \n",
|
||
"z\n",
|
||
"M 3481 434 \n",
|
||
"Q 3481 -459 3084 -895 \n",
|
||
"Q 2688 -1331 1869 -1331 \n",
|
||
"Q 1566 -1331 1297 -1286 \n",
|
||
"Q 1028 -1241 775 -1147 \n",
|
||
"L 775 -588 \n",
|
||
"Q 1028 -725 1275 -790 \n",
|
||
"Q 1522 -856 1778 -856 \n",
|
||
"Q 2344 -856 2625 -561 \n",
|
||
"Q 2906 -266 2906 331 \n",
|
||
"L 2906 616 \n",
|
||
"Q 2728 306 2450 153 \n",
|
||
"Q 2172 0 1784 0 \n",
|
||
"Q 1141 0 747 490 \n",
|
||
"Q 353 981 353 1791 \n",
|
||
"Q 353 2603 747 3093 \n",
|
||
"Q 1141 3584 1784 3584 \n",
|
||
"Q 2172 3584 2450 3431 \n",
|
||
"Q 2728 3278 2906 2969 \n",
|
||
"L 2906 3500 \n",
|
||
"L 3481 3500 \n",
|
||
"L 3481 434 \n",
|
||
"z\n",
|
||
"\" transform=\"scale(0.015625)\"/>\n",
|
||
" </defs>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-61\" x=\"39.208984\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-72\" x=\"100.488281\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-67\" x=\"139.851562\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-65\" x=\"203.328125\"/>\n",
|
||
" <use xlink:href=\"#DejaVuSans-74\" x=\"264.851562\"/>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" </g>\n",
|
||
" <defs>\n",
|
||
" <clipPath id=\"p4f217efe07\">\n",
|
||
" <rect x=\"66.053125\" y=\"7.2\" width=\"195.3\" height=\"135.9\"/>\n",
|
||
" </clipPath>\n",
|
||
" </defs>\n",
|
||
" <defs>\n",
|
||
" <pattern id=\"h446a4b1fc9\" patternUnits=\"userSpaceOnUse\" x=\"0\" y=\"0\" width=\"72\" height=\"72\">\n",
|
||
" <rect x=\"0\" y=\"0\" width=\"73\" height=\"73\" fill=\"#ff7f0e\"/>\n",
|
||
" <path d=\"M -36 36 \n",
|
||
"L 36 -36 \n",
|
||
"M -24 48 \n",
|
||
"L 48 -24 \n",
|
||
"M -12 60 \n",
|
||
"L 60 -12 \n",
|
||
"M 0 72 \n",
|
||
"L 72 0 \n",
|
||
"M 12 84 \n",
|
||
"L 84 12 \n",
|
||
"M 24 96 \n",
|
||
"L 96 24 \n",
|
||
"M 36 108 \n",
|
||
"L 108 36 \n",
|
||
"\" style=\"fill: #000000; stroke: #000000; stroke-width: 1.0; stroke-linecap: butt; stroke-linejoin: miter\"/>\n",
|
||
" </pattern>\n",
|
||
" </defs>\n",
|
||
"</svg>\n"
|
||
],
|
||
"text/plain": [
|
||
"<Figure size 252x180 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"def show_list_len_pair_hist(legend, xlabel, ylabel, xlist, ylist):\n",
|
||
" \"\"\"绘制列表长度对的直方图\"\"\"\n",
|
||
" d2l.set_figsize()\n",
|
||
" _, _, patches = d2l.plt.hist(\n",
|
||
" [[len(l) for l in xlist], [len(l) for l in ylist]])\n",
|
||
" d2l.plt.xlabel(xlabel)\n",
|
||
" d2l.plt.ylabel(ylabel)\n",
|
||
" for patch in patches[1].patches:\n",
|
||
" patch.set_hatch('/')\n",
|
||
" d2l.plt.legend(legend)\n",
|
||
"\n",
|
||
"show_list_len_pair_hist(['source', 'target'], '# tokens per sequence',\n",
|
||
" 'count', source, target);"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "26e67b14",
|
||
"metadata": {
|
||
"origin_pos": 13
|
||
},
|
||
"source": [
|
||
"## [**词表**]\n",
|
||
"\n",
|
||
"由于机器翻译数据集由语言对组成，\n",
|
||
"因此我们可以分别为源语言和目标语言构建两个词表。\n",
|
||
"使用单词级词元化时，词表大小将明显大于使用字符级词元化时的词表大小。\n",
|
||
"为了缓解这一问题，这里我们将出现次数少于2次的低频率词元\n",
|
||
"视为相同的未知（“<unk>”）词元。\n",
|
||
"除此之外，我们还指定了额外的特定词元，\n",
|
||
"例如在小批量时用于将序列填充到相同长度的填充词元（“<pad>”），\n",
|
||
"以及序列的开始词元（“<bos>”）和结束词元（“<eos>”）。\n",
|
||
"这些特殊词元在自然语言处理任务中比较常用。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "1179a522",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.732422Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.731864Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.957959Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.957157Z"
|
||
},
|
||
"origin_pos": 14,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"10012"
|
||
]
|
||
},
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"src_vocab = d2l.Vocab(source, min_freq=2,\n",
|
||
" reserved_tokens=['<pad>', '<bos>', '<eos>'])\n",
|
||
"len(src_vocab)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "216c91b5",
|
||
"metadata": {
|
||
"origin_pos": 15
|
||
},
|
||
"source": [
|
||
"## 加载数据集\n",
|
||
":label:`subsec_mt_data_loading`\n",
|
||
"\n",
|
||
"回想一下，语言模型中的[**序列样本都有一个固定的长度**]，\n",
|
||
"无论这个样本是一个句子的一部分还是跨越了多个句子的一个片断。\n",
|
||
"这个固定长度是由 :numref:`sec_language_model`中的\n",
|
||
"`num_steps`（时间步数或词元数量）参数指定的。\n",
|
||
"在机器翻译中，每个样本都是由源和目标组成的文本序列对，\n",
|
||
"其中的每个文本序列可能具有不同的长度。\n",
|
||
"\n",
|
||
"为了提高计算效率，我们仍然可以通过*截断*（truncation）和\n",
|
||
"*填充*（padding）方式实现一次只处理一个小批量的文本序列。\n",
|
||
"假设同一个小批量中的每个序列都应该具有相同的长度`num_steps`，\n",
|
||
"那么如果文本序列的词元数目少于`num_steps`时，\n",
|
||
"我们将继续在其末尾添加特定的“<pad>”词元，\n",
|
||
"直到其长度达到`num_steps`；\n",
|
||
"反之，我们将截断文本序列时，只取其前`num_steps` 个词元，\n",
|
||
"并且丢弃剩余的词元。这样，每个文本序列将具有相同的长度，\n",
|
||
"以便以相同形状的小批量进行加载。\n",
|
||
"\n",
|
||
"如前所述，下面的`truncate_pad`函数将(**截断或填充文本序列**)。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "42aa524a",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.962377Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.961250Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.968643Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.967892Z"
|
||
},
|
||
"origin_pos": 16,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"[47, 4, 1, 1, 1, 1, 1, 1, 1, 1]"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"#@save\n",
|
||
"def truncate_pad(line, num_steps, padding_token):\n",
|
||
" \"\"\"截断或填充文本序列\"\"\"\n",
|
||
" if len(line) > num_steps:\n",
|
||
" return line[:num_steps] # 截断\n",
|
||
" return line + [padding_token] * (num_steps - len(line)) # 填充\n",
|
||
"\n",
|
||
"truncate_pad(src_vocab[source[0]], 10, src_vocab['<pad>'])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2974b660",
|
||
"metadata": {
|
||
"origin_pos": 17
|
||
},
|
||
"source": [
|
||
"现在我们定义一个函数，可以将文本序列\n",
|
||
"[**转换成小批量数据集用于训练**]。\n",
|
||
"我们将特定的“<eos>”词元添加到所有序列的末尾，\n",
|
||
"用于表示序列的结束。\n",
|
||
"当模型通过一个词元接一个词元地生成序列进行预测时，\n",
|
||
"生成的“<eos>”词元说明完成了序列输出工作。\n",
|
||
"此外，我们还记录了每个文本序列的长度，\n",
|
||
"统计长度时排除了填充词元，\n",
|
||
"在稍后将要介绍的一些模型会需要这个长度信息。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "db17050b",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.973483Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.972873Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.978080Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.977330Z"
|
||
},
|
||
"origin_pos": 18,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def build_array_nmt(lines, vocab, num_steps):\n",
|
||
" \"\"\"将机器翻译的文本序列转换成小批量\"\"\"\n",
|
||
" lines = [vocab[l] for l in lines]\n",
|
||
" lines = [l + [vocab['<eos>']] for l in lines]\n",
|
||
" array = torch.tensor([truncate_pad(\n",
|
||
" l, num_steps, vocab['<pad>']) for l in lines])\n",
|
||
" valid_len = (array != vocab['<pad>']).type(torch.int32).sum(1)\n",
|
||
" return array, valid_len"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "85e2af67",
|
||
"metadata": {
|
||
"origin_pos": 19
|
||
},
|
||
"source": [
|
||
"## [**训练模型**]\n",
|
||
"\n",
|
||
"最后，我们定义`load_data_nmt`函数来返回数据迭代器，\n",
|
||
"以及源语言和目标语言的两种词表。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "8addcc51",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.982873Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.982349Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:37.988101Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:37.987357Z"
|
||
},
|
||
"origin_pos": 20,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@save\n",
|
||
"def load_data_nmt(batch_size, num_steps, num_examples=600):\n",
|
||
" \"\"\"返回翻译数据集的迭代器和词表\"\"\"\n",
|
||
" text = preprocess_nmt(read_data_nmt())\n",
|
||
" source, target = tokenize_nmt(text, num_examples)\n",
|
||
" src_vocab = d2l.Vocab(source, min_freq=2,\n",
|
||
" reserved_tokens=['<pad>', '<bos>', '<eos>'])\n",
|
||
" tgt_vocab = d2l.Vocab(target, min_freq=2,\n",
|
||
" reserved_tokens=['<pad>', '<bos>', '<eos>'])\n",
|
||
" src_array, src_valid_len = build_array_nmt(source, src_vocab, num_steps)\n",
|
||
" tgt_array, tgt_valid_len = build_array_nmt(target, tgt_vocab, num_steps)\n",
|
||
" data_arrays = (src_array, src_valid_len, tgt_array, tgt_valid_len)\n",
|
||
" data_iter = d2l.load_array(data_arrays, batch_size)\n",
|
||
" return data_iter, src_vocab, tgt_vocab"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6afba4ea",
|
||
"metadata": {
|
||
"origin_pos": 21
|
||
},
|
||
"source": [
|
||
"下面我们[**读出“英语－法语”数据集中的第一个小批量数据**]。\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "90df834d",
|
||
"metadata": {
|
||
"execution": {
|
||
"iopub.execute_input": "2023-08-18T07:07:37.992732Z",
|
||
"iopub.status.busy": "2023-08-18T07:07:37.992204Z",
|
||
"iopub.status.idle": "2023-08-18T07:07:43.780428Z",
|
||
"shell.execute_reply": "2023-08-18T07:07:43.779613Z"
|
||
},
|
||
"origin_pos": 22,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"X: tensor([[ 7, 43, 4, 3, 1, 1, 1, 1],\n",
|
||
" [44, 23, 4, 3, 1, 1, 1, 1]], dtype=torch.int32)\n",
|
||
"X的有效长度: tensor([4, 4])\n",
|
||
"Y: tensor([[ 6, 7, 40, 4, 3, 1, 1, 1],\n",
|
||
" [ 0, 5, 3, 1, 1, 1, 1, 1]], dtype=torch.int32)\n",
|
||
"Y的有效长度: tensor([5, 3])\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"train_iter, src_vocab, tgt_vocab = load_data_nmt(batch_size=2, num_steps=8)\n",
|
||
"for X, X_valid_len, Y, Y_valid_len in train_iter:\n",
|
||
" print('X:', X.type(torch.int32))\n",
|
||
" print('X的有效长度:', X_valid_len)\n",
|
||
" print('Y:', Y.type(torch.int32))\n",
|
||
" print('Y的有效长度:', Y_valid_len)\n",
|
||
" break"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "df773107",
|
||
"metadata": {
|
||
"origin_pos": 23
|
||
},
|
||
"source": [
|
||
"## 小结\n",
|
||
"\n",
|
||
"* 机器翻译指的是将文本序列从一种语言自动翻译成另一种语言。\n",
|
||
"* 使用单词级词元化时的词表大小，将明显大于使用字符级词元化时的词表大小。为了缓解这一问题，我们可以将低频词元视为相同的未知词元。\n",
|
||
"* 通过截断和填充文本序列，可以保证所有的文本序列都具有相同的长度，以便以小批量的方式加载。\n",
|
||
"\n",
|
||
"## 练习\n",
|
||
"\n",
|
||
"1. 在`load_data_nmt`函数中尝试不同的`num_examples`参数值。这对源语言和目标语言的词表大小有何影响？\n",
|
||
"1. 某些语言（例如中文和日语）的文本没有单词边界指示符（例如空格）。对于这种情况，单词级词元化仍然是个好主意吗？为什么？\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "439397fa",
|
||
"metadata": {
|
||
"origin_pos": 25,
|
||
"tab": [
|
||
"pytorch"
|
||
]
|
||
},
|
||
"source": [
|
||
"[Discussions](https://discuss.d2l.ai/t/2776)\n"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"language_info": {
|
||
"name": "python"
|
||
},
|
||
"required_libs": []
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
} |