def make_windowed_data(data, start, end, window_size = 1): """Uses the input sequences in @data to construct new windowed data points.TODO: In the code below, construct a window from each word in the input sentence by concatenating the words @window_size to the left and @window_size to the right to the word. Finally, add this new window data point and its label. to windowed_data.Args: data: is a list of (sentence, labels) tuples. @sentence is a list containing the words in the sentence and @label is a list of output labels. Each word is itself a list of @n_features features. For example, the sentence "Chris Manning is amazing" and labels "PER PER O O" would become ([[1,9], [2,9], [3,8], [4,8]], [1, 1, 4, 4]). Here "Chris" the word has been featurized as "[1, 9]", and "[1, 1, 4, 4]" is the list of labels. start: the featurized `start' token to be used for windows at the very beginning of the sentence. end: the featurized `end' token to be used for windows at the very end of the sentence. window_size: the length of the window to construct. Returns: a new list of data points, corresponding to each window in the sentence. Each data point consists of a list of @n_window_features features (corresponding to words from the window) to be used in the sentence and its NER label. If start=[5,8] and end=[6,8], the above example should return the list [([5, 8, 1, 9, 2, 9], 1), ([1, 9, 2, 9, 3, 8], 1), ... ] """windowed_data = [] for sentence, labels in data: # YOUR CODE HERE (5-20 lines) T = len(labels)# 序列长度T for t in range(T):# 遍历单个序列的每个单词 sen2fea = [] for l in range(window_size, 0, -1):# 左窗口的w个单词 if t-l < 0: sen2fea.extend(start) else: sen2fea.extend(sentence[t-l]) sen2fea.extend(sentence[t]) for r in range(1, window_size+1):# 右窗口的w个单词 if t+r >= T: sen2fea.extend(end) else: sen2fea.extend(sentence[t+r]) windowed_data.append((sen2fea, labels[t])) # END YOUR CODE return windowed_data

class WindowModel(NERModel): """ Implements a feedforward neural network with an embedding layer and single hidden layer. This network will predict what label (e.g. PER) should be given to a given token (e.g. Manning) byusing a featurized window around the token. """def add_placeholders(self): """Generates placeholder variables to represent the input tensorsThese placeholders are used as inputs by the rest of the model building and will be fed data during training.Note that when "None" is in a placeholder's shape, it's flexible (so we can use different batch sizes without rebuilding the model).Adds following nodes to the computational graphinput_placeholder: Input placeholder tensor ofshape (None, n_window_features), type tf.int32 labels_placeholder: Labels placeholder tensor of shape (None,), type tf.int32 dropout_placeholder: Dropout value placeholder (scalar), type tf.float32Add these placeholders to self as the instance variables self.input_placeholder self.labels_placeholder self.dropout_placeholder(Don't change the variable names) """ # YOUR CODE HERE (~3-5 lines) self.input_placeholder = tf.placeholder(shape=[None, Config.n_window_features], dtype=tf.int32) self.labels_placeholder = tf.placeholder(shape=[None, ], dtype=tf.int32) self.dropout_placeholder = tf.placeholder(dtype=tf.float32) # END YOUR CODEdef create_feed_dict(self, inputs_batch, labels_batch=None, dropout=1): """Creates the feed_dict for the model. A feed_dict takes the form of: feed_dict = {: , .... }Hint: The keys for the feed_dict should be a subset of the placeholder tensors created in add_placeholders. Hint: When an argument is None, don't add it to the feed_dict.Args: inputs_batch: A batch of input data. labels_batch: A batch of label data. dropout: The dropout rate. Returns: feed_dict: The feed dictionary mapping from placeholders to values. """ # YOUR CODE HERE (~5-10 lines) if labels_batch is None: feed_dict = {self.input_placeholder: inputs_batch, self.dropout_placeholder: dropout} else: feed_dict = {self.input_placeholder: inputs_batch, self.labels_placeholder: labels_batch, self.dropout_placeholder: dropout} # END YOUR CODE return feed_dictdef add_embedding(self): """Adds an embedding layer that maps from input tokens (integers) to vectors and then concatenates those vectors: - Creates an embedding tensor and initializes it with self.pretrained_embeddings. - Uses the input_placeholder to index into the embeddings tensor, resulting in a tensor of shape (None, n_window_features, embedding_size). - Concatenates the embeddings by reshaping the embeddings tensor to shape (None, n_window_features * embedding_size).Hint: You might find tf.nn.embedding_lookup useful. Hint: You can use tf.reshape to concatenate the vectors. See following link to understand what -1 in a shape means. https://www.tensorflow.org/api_docs/python/array_ops/shapes_and_shaping#reshape. Returns: embeddings: tf.Tensor of shape (None, n_window_features*embed_size) """ # YOUR CODE HERE (!3-5 lines) embedding = tf.Variable(self.pretrained_embeddings, name='embedding') embeddings_3d = tf.nn.embedding_lookup(embedding, self.input_placeholder) embeddings = tf.reshape(embeddings_3d, shape=[-1, Config.n_window_features*Config.embed_size]) # END YOUR CODE return embeddingsdef add_prediction_op(self): """Adds the 1-hidden-layer NN: h = Relu(xW + b1) h_drop = Dropout(h, dropout_rate) pred = h_dropU + b2Recall that we are not applying a softmax to pred. The softmax will instead be done in the add_loss_op function, which improves efficiency because we can use tf.nn.softmax_cross_entropy_with_logitsWhen creating a new variable, use the tf.get_variable function because it lets us specify an initializer.Use tf.contrib.layers.xavier_initializer to initialize matrices. This is TensorFlow's implementation of the Xavier initialization trick we used in last assignment.Note: tf.nn.dropout takes the keep probability (1 - p_drop) as an argument. The keep probability should be set to the value of dropout_rate.Returns: pred: tf.Tensor of shape (batch_size, n_classes) """x = self.add_embedding() dropout_rate = self.dropout_placeholder # YOUR CODE HERE (~10-20 lines) W = tf.get_variable(initializer=tf.contrib.layers.xavier_initializer(), shape=[Config.n_window_features*Config.embed_size, Config.hidden_size], name='W') b1 = tf.get_variable(initializer=tf.zeros(Config.hidden_size), name='b1') h = tf.nn.relu(tf.matmul(x, W) + b1) h_drop = tf.nn.dropout(h, keep_prob=dropout_rate) U = tf.get_variable(initializer=tf.contrib.layers.xavier_initializer(), shape=[Config.hidden_size, Config.n_classes], name='U') b2 = tf.get_variable(initializer=tf.zeros(Config.n_classes), name='b2') pred = tf.matmul(h_drop, U) + b2 # END YOUR CODE return preddef add_loss_op(self, pred): """Adds Ops for the loss function to the computational graph. In this case we are using cross entropy loss. The loss should be averaged over all examples in the current minibatch.Remember that you can use tf.nn.sparse_softmax_cross_entropy_with_logits to simplify your implementation. You might find tf.reduce_mean useful. Args: pred: A tensor of shape (batch_size, n_classes) containing the output of the neural network before the softmax layer. Returns: loss: A 0-d tensor (scalar) """ # YOUR CODE HERE (~2-5 lines) loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=pred, labels=self.labels_placeholder)) # END YOUR CODE return lossdef add_training_op(self, loss): """Sets up the training Ops.Creates an optimizer and applies the gradients to all trainable variables. The Op returned by this function is what must be passed to the `sess.run()` call to cause the model to train. Seehttps://www.tensorflow.org/versions/r0.7/api_docs/python/train.html#Optimizerfor more information.Use tf.train.AdamOptimizer for this model. Calling optimizer.minimize() will return a train_op object.Args: loss: Loss tensor, from cross_entropy_loss. Returns: train_op: The Op for training. """ # YOUR CODE HERE (~1-2 lines) train_op = tf.train.AdamOptimizer(learning_rate=Config.lr).minimize(loss) # END YOUR CODE return train_opdef preprocess_sequence_data(self, examples): return make_windowed_data(examples, start=self.helper.START, end=self.helper.END, window_size=self.config.window_size)def consolidate_predictions(self, examples_raw, examples, preds): """Batch the predictions into groups of sentence length. """ ret = [] #pdb.set_trace() i = 0 for sentence, labels in examples_raw: labels_ = preds[i:i+len(sentence)] i += len(sentence) ret.append([sentence, labels, labels_]) return retdef predict_on_batch(self, sess, inputs_batch): """Make predictions for the provided batch of dataArgs: sess: tf.Session() input_batch: np.ndarray of shape (n_samples, n_features) Returns: predictions: np.ndarray of shape (n_samples, n_classes) """ feed = self.create_feed_dict(inputs_batch) predictions = sess.run(tf.argmax(self.pred, axis=1), feed_dict=feed) return predictionsdef train_on_batch(self, sess, inputs_batch, labels_batch): feed = self.create_feed_dict(inputs_batch, labels_batch=labels_batch, dropout=self.config.dropout) _, loss = sess.run([self.train_op, self.loss], feed_dict=feed) return lossdef __init__(self, helper, config, pretrained_embeddings, report=None): super(WindowModel, self).__init__(helper, config, report) self.pretrained_embeddings = pretrained_embeddings# Defining placeholders. self.input_placeholder = None self.labels_placeholder = None self.dropout_placeholder = Noneself.build()

/中，results.txt包含了模型在验证集上的预测的格式化输出，log文件包含了打印出来的输出，即训练中计算得到的混淆矩阵和F1值。

文章图片

(d)使用上面生成的文件分析模型的预测。
i.简要描述混淆矩阵显示的关于模型预测错误的信息。
混淆矩阵显示模型的最大混淆源来自组织标签，其中许多组织被误认为人名或直接被忽略，另一方面，人名似乎被识别的很好。
【NLP|CS224N刷题——Assignment3.1_A window into NER】ii.描述基于窗口的模型的至少2个建模限制。
基于窗口的模型不能使用来自相邻预测的信息来消除标签决策的歧义，从而导致不连续的实体预测。

关于tf.Variable和tf.get_variable的区别：
https://blog.csdn.net/MrR1ght/article/details/81228087
关于tf.nn.embedding_lookup：
https://blog.csdn.net/yinruiyang94/article/details/77600453
https://tensorflow.google.cn/api_docs/python/tf/nn/embedding_lookup
关于tf.contrib.layers.xavier_initializer：
https://blog.csdn.net/yinruiyang94/article/details/78354257
https://tensorflow.google.cn/api_docs/python/tf/contrib/layers/xavier_initializer

推荐阅读

• 

  一个锅炉能烧热吗为什么，怎么修复与排查方法？
• 

  梦见偷白菜是什么意思 梦见偷白菜是什么意思打牌财运怎么样
• 

  秋葵吃起来苦是什么原因
• 

  酒精|除了头孢 服这7类药饮酒也致死
• 

  胖子学滑板技巧
• 

  青岛适合婚纱外景的拍摄地点有哪些
• 

  跳绳后不拉伸腿会怎样
• 

  飞利浦FC5122吸尘器不吸尘是怎么回事
• 

  刘德华曾叫洪金宝大哥，但被洪金宝出卖，并且还被他算计
• 

  cad软件下载,国产免费cad软件下载
• 

  怎么追很熟悉的女生 很熟的女生好追吗
• 

  入侵检测需求分析
• 

  电信大王卡有短信功能吗？
• 

  linux停止打印命令 linux 停止
• 

  如何应对静默登录服务器繁忙的情况？ 静默登录服务器繁忙怎么办
• 

  kn95口罩分医用和非医用区别
• 

  吃金蝉过敏能吹风扇吗
• 

  网关地址指的是什么
• 

  胎位不正 孕妇要小心这些症状表现
• 

  一篇关于对学生进行危机干预的听课笔记

• 人工智能|hugginface-introduction 案例介绍
• 深度学习|论文阅读（《Deep Interest Evolution Network for Click-Through Rate Prediction》）
• nlp|Keras(十一)梯度带(GradientTape)的基本使用方法，与tf.keras结合使用
• NER|[论文阅读笔记01]Neural Architectures for Nested NER through Linearization
• 深度学习|2019年CS224N课程笔记-Lecture 17:Multitask Learning
• 深度学习|[深度学习] 一篇文章理解 word2vec
• 论文|预训练模型综述2020年三月《Pre-trained Models for Natural Language Processing: A Survey》
• NLP|NLP预训练模型综述
• NLP之文本表示——二值文本表示
• 隐马尔科夫HMM应用于中文分词