【Mo 人工智能技术博客】使用 Seq2Seq 实现中英文翻译
1. 介绍
1.1 Deep NLP
1.2 来由
Seq2Seq Model是序列到序列( Sequence to Sequence )模型的简称,也被称为一种编码器-解码器(Encoder-Decoder)模型,分别基于2014发布的两篇论文:
- Sequence to Sequence Learning with Neural Networks by Sutskever et al.,
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation by Cho et al.,
2. Seq2Seq Model 之不断探索
3. 中英文翻译
到了我们动手的时刻了,理解了上面 Seq2Seq 模型,让我们搭建一个简单的中英文翻译模型。
3.1 数据集
我们使用 manythings 网站的一个中英文数据集,现已经上传到 Mo 平台了,点击查看。该数据集格式为英文+tab+中文。
3.2 处理数据
from keras.models import Model
from keras.layers import Input, LSTM, Dense
import numpy as npbatch_size = 64 # Batch size for training.
epochs = 100 # Number of epochs to train for.
latent_dim = 256 # Latent dimensionality of the encoding space.
num_samples = 10000 # Number of samples to train on.
# Path to the data txt file on disk.
data_path = 'cmn.txt'# Vectorize the data.
input_texts = []
target_texts = []
input_characters = set()
target_characters = set()
with open(data_path, 'r', encoding='utf-8') as f:lines = f.read().split('\n')
for line in lines[: min(num_samples, len(lines) - 1)]:input_text, target_text = line.split('\t')# We use "tab" as the "start sequence" character# for the targets, and "\n" as "end sequence" character.target_text = '\t' + target_text + '\n'input_texts.append(input_text)target_texts.append(target_text)for char in input_text:if char not in input_characters:input_characters.add(char)for char in target_text:if char not in target_characters:target_characters.add(char)input_characters = sorted(list(input_characters))
target_characters = sorted(list(target_characters))
num_encoder_tokens = len(input_characters)
num_decoder_tokens = len(target_characters)
max_encoder_seq_length = max([len(txt) for txt in input_texts])
max_decoder_seq_length = max([len(txt) for txt in target_texts])print('Number of samples:', len(input_texts))
print('Number of unique input tokens:', num_encoder_tokens)
print('Number of unique output tokens:', num_decoder_tokens)
print('Max sequence length for inputs:', max_encoder_seq_length)
print('Max sequence length for outputs:', max_decoder_seq_length)
3.3 Encoder-LSTM
# mapping token to index, easily to vectors
input_token_index = dict([(char, i) for i, char in enumerate(input_characters)])
target_token_index = dict([(char, i) for i, char in enumerate(target_characters)])# np.zeros(shape, dtype, order)
# shape is an tuple, in here 3D
encoder_input_data = np.zeros((len(input_texts), max_encoder_seq_length, num_encoder_tokens),dtype='float32')
decoder_input_data = np.zeros((len(input_texts), max_decoder_seq_length, num_decoder_tokens),dtype='float32')
decoder_target_data = np.zeros((len(input_texts), max_decoder_seq_length, num_decoder_tokens),dtype='float32')# input_texts contain all english sentences
# output_texts contain all chinese sentences
# zip('ABC','xyz') ==> Ax By Cz, looks like that
# the aim is: vectorilize text, 3D
for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):for t, char in enumerate(input_text):# 3D vector only z-index has char its value equals 1.0encoder_input_data[i, t, input_token_index[char]] = 1.for t, char in enumerate(target_text):# decoder_target_data is ahead of decoder_input_data by one timestepdecoder_input_data[i, t, target_token_index[char]] = 1.if t > 0:# decoder_target_data will be ahead by one timestep# and will not include the start character.# igone t=0 and start t=1, means decoder_target_data[i, t - 1, target_token_index[char]] = 1.
3.4 Context(hidden state)
# Define an input sequence and process it.
# input prodocts keras tensor, to fit keras model!
# 1x73 vector
# encoder_inputs is a 1x73 tensor!
encoder_inputs = Input(shape=(None, num_encoder_tokens))# units=256, return the last state in addition to the output
encoder_lstm = LSTM((latent_dim), return_state=True)# LSTM(tensor) return output, state-history, state-current
encoder_outputs, state_h, state_c = encoder_lstm(encoder_inputs)# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]
3.5 Decoder-LSTM
# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = LSTM((latent_dim), return_sequences=True, return_state=True)# obtain output
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,initial_state=encoder_states)# dense 2580x1 units full connented layer
decoder_dense = Dense(num_decoder_tokens, activation='softmax')# why let decoder_outputs go through dense ?
decoder_outputs = decoder_dense(decoder_outputs)# Define the model that will turn, groups layers into an object
# with training and inference features
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
# model(input, output)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)# Run training
# compile -> configure model for training
model.compile(optimizer='rmsprop', loss='categorical_crossentropy')
# model optimizsm
model.fit([encoder_input_data, decoder_input_data], decoder_target_data,batch_size=batch_size,epochs=epochs,validation_split=0.2)
# Save model
model.save('seq2seq.h5')
3.6 解码序列
# Define sampling models
encoder_model = Model(encoder_inputs, encoder_states)
decoder_state_input_h = Input(shape=(latent_dim,))
decoder_state_input_c = Input(shape=(latent_dim,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model([decoder_inputs] + decoder_states_inputs,[decoder_outputs] + decoder_states)# Reverse-lookup token index to decode sequences back to
# something readable.
reverse_input_char_index = dict((i, char) for char, i in input_token_index.items())
reverse_target_char_index = dict((i, char) for char, i in target_token_index.items())def decode_sequence(input_seq):# Encode the input as state vectors.states_value = encoder_model.predict(input_seq)# Generate empty target sequence of length 1.target_seq = np.zeros((1, 1, num_decoder_tokens))# Populate the first character of target sequence with the start character.target_seq[0, 0, target_token_index['\t']] = 1.# this target_seq you can treat as initial state# Sampling loop for a batch of sequences# (to simplify, here we assume a batch of size 1).stop_condition = Falsedecoded_sentence = ''while not stop_condition:output_tokens, h, c = decoder_model.predict([target_seq] + states_value)# Sample a token# argmax: Returns the indices of the maximum values along an axis# just like find the most possible charsampled_token_index = np.argmax(output_tokens[0, -1, :])# find char using indexsampled_char = reverse_target_char_index[sampled_token_index]# and append sentencedecoded_sentence += sampled_char# Exit condition: either hit max length# or find stop character.if (sampled_char == '\n' or len(decoded_sentence) > max_decoder_seq_length):stop_condition = True# Update the target sequence (of length 1).# append then ?# creating another new target_seq# and this time assume sampled_token_index to 1.0target_seq = np.zeros((1, 1, num_decoder_tokens))target_seq[0, 0, sampled_token_index] = 1.# Update states# update states, frome the front partsstates_value = [h, c]return decoded_sentence
3.7 预测
for seq_index in range(100,200):# Take one sequence (part of the training set)# for trying out decoding.input_seq = encoder_input_data[seq_index: seq_index + 1]decoded_sentence = decode_sequence(input_seq)print('Input sentence:', input_texts[seq_index])print('Decoded sentence:', decoded_sentence)
该项目已公开在 Mo 平台上,Seq2Seq之中英文翻译,建议使用GPU训练。
介绍 Mo 平台一个非常贴心实用的功能: API Doc,(在开发界面的右侧栏,第二个)。
在 Mo 平台写代码可以很方便的实现多窗口显示,只要拖动窗口的标题栏就可实现分栏。
4. 总结与展望
5. 引用
【Mo 人工智能技术博客】使用 Seq2Seq 实现中英文翻译相关推荐
- 【Mo 人工智能技术博客】StarGAN——生成你的明星脸
1 GAN 介绍 GAN,叫做生成对抗网络 (Generative Adversarial Network) .其基本原理是生成器网络 G(Generator) 和判别器网络 D(Discrimina ...
- 【Mo 人工智能技术博客】多标准中文分词 Multi-Criteria-CWS
多标准中文分词 Multi-Criteria-CWS 作者:宋彤彤 自然语言处理(NLP)是人工智能中很重要且具有挑战性的方向,而自然语言处理的第一步就是分词,分词的效果直接决定和影响后续工作的效率. ...
- 【Mo 人工智能技术博客】胶囊网络——Capsule Network
胶囊网络--Capsule Network 作者:林泽龙 1. 背景介绍 CNN 在处理图像分类问题上表现非常出色,已经完成了很多不可思议的任务,并且在一些项目上超过了人类,对整个机器学习的领域产生了 ...
- 【Mo 人工智能技术博客】基于耦合网络的推荐系统
基于耦合网络的推荐系统 作者:陈东瑞 1.复杂网络基础知识 当我们拿起手机给家人.朋友或者同事拨打电话时,就不知不觉中参与到了社交网络形成的过程中:当我们登上高铁或者飞机时,就可以享受交通网络给我们带 ...
- 【Mo 人工智能技术博客】现在最流行的图神经网络库 pytorch geometric 上手教学
简介 Graph Neural Networks 简称 GNN,称为图神经网络.近年来 GNN 在学术界受到的关注越来越多,与之相关的论文数量呈上升趋势,GNN 通过对信息的传递,转换和聚合实现特征的 ...
- 【Mo 人工智能技术博客】利用Logistic函数和LSTM分析疫情数据
利用Logistic函数和LSTM分析疫情数据 作者:林泽龙 Mo 1. 背景 2019 新型冠状病毒 (SARS-CoV-2),曾用名 2019-nCoV,通用简称新冠病毒,是一种具有包膜的正链单股 ...
- 【Mo 人工智能技术博客】采用 Python 机器学习预测足球比赛结果
采用 Python 机器学习预测足球比赛结果 足球是世界上最火爆的运动之一,世界杯期间也往往是球迷们最亢奋的时刻.比赛狂欢季除了炸出了熬夜看球的铁杆粉丝,也让足球竞猜也成了大家茶余饭后最热衷的话题.甚 ...
- 【Mo 人工智能技术博客】基于 Python 和 NLTK 的推特情感分析
基于 Python 和 NLTK 的推特情感分析 作者:宋彤彤 1. 导读 NLTK 是 Python 的一个自然语言处理模块,其中实现了朴素贝叶斯分类算法.这次 Mo 来教大家如何通过 python ...
- 【Mo 人工智能技术博客】时间序列预测——DA-RNN模型
时间序列预测--DA-RNN模型 作者:梅昊铭 1. 背景介绍 传统的用于时间序列预测的非线性自回归模型(NRAX)很难捕捉到一段较长的时间内的数据间的时间相关性并选择相应的驱动数据来进行预测.本文将 ...
最新文章
- JNDI学习总结(1)——JNDI入门
- 简单易用的倒计时js代码
- 斐波那契数列python递归 0、1、1、2、3_python: 递归和递推方法求斐波那契数列
- 基于Azure Blob冷存储的数据压缩备份总结
- mysql删除bin-log_删除MYSQl BIN-LOG 日志
- jpypePython对象转JAVA_通过JPype和numpy将Java类型转换为Python
- Python压缩多个属于不同驱动器的文件夹至同一个zip文件
- [leetcode-117]填充每个节点的下一个右侧节点指针 II
- iPhone SDK开发基础之UIPageControl编程
- java 加密压缩文件
- 彻底改变计算机用户名,提升电脑系统安全:如何修改电脑登录用户名以及密码呢?...
- u盘安装centos8黑屏_u盘centos7 安装 黑屏苹果电脑怎么安装win7系统还原
- 什么是SEO,为什么要做SEO?
- 书单|互联网企业面试案头书之程序员软技能篇
- Js 限时秒杀【倒计时】【案例】
- C# 画板 Drawing
- 51单片机设计多功能电子秤(实训项目)
- 浙江邦盛科技-面试总结(offer)
- 犇牛的防御-写给公司的邮件
- minist手写识别 cifar图片
热门文章
- 20220513-rk3568编译linux4.19的buildroot4-(rootrs)
- 校园网WIFI之云免流历程总结 原创
- 测度上Lebesgue积分的确定
- pub格式的文件打开报错:Publisher无法打开文件 解决办法
- Tryhackme-Cryptography
- 数据结构——用栈实现后缀表达式的计算
- python通过键盘方向键移动_平滑地通过键盘移动角色示例.py
- 含稀土铕双功能荧光磁性纳米粒子/包裹磁性稀土荧光复合物纳米微球的性能与表征
- android触摸效果,Android开发进阶:仿MIUI12控件触摸反馈效果(下沉+倾斜)附源码...
- 高铝水泥与硅酸盐水泥或石灰混合使用