pipeline:
- name: "SpacyNLP"
# language model to load
model: "en_core_web_md"
# when retrieving word vectors, this will decide if the casing
# of the word is relevant. E.g. `hello` and `Hello` will
# retrieve the same vector, if set to `false`. For some
# applications and models it makes sense to differentiate
# between these two words, therefore setting this to `true`.
case_sensitive: false
通过analyzer参数能将featurizer配置为 word 或 character n-grams。默认下，analyzer是设置为 word，所以 word token计数作为特征。如果想要设置为character n-grams可以将analyzer设置为char 或 char_wb。char_wb仅从单词边界内的文本创建character n-grams;单词边缘的n-gram用空格填充。此选项可用于创建Subword Semantic Hashing。对于character n-grams，不要忘记增加min_ngram和max_ngram参数。否则，词汇表将只包含单个字母。另外，在处理OOV上，由于训练是在有限的词汇数据上进行的，因此不能保证在预测过程中算法不会遇到未知的单词(在训练过程中没有看到的单词，即OOV)。为了教算法如何处理未知的单词，训练数据中的一些单词可以用通用单词OOV_token代替。在这种情况下，在预测期间，所有未知单词将被视为通用单词OOV_token。
pipeline:
- name: "CountVectorsFeaturizer"
# whether to use a shared vocab
"use_shared_vocab": False,
# whether to use word or character n-grams
# 'char_wb' creates character n-grams only inside word boundaries
# n-grams at the edges of words are padded with space.
analyzer: 'word' # use 'char' or 'char_wb' for character
# the parameters are taken from
# sklearn's CountVectorizer
# regular expression for tokens
token_pattern: r'(?u)\b\w\w+\b'
# remove accents during the preprocessing step
strip_accents: None # {'ascii', 'unicode', None}
# list of stop words
stop_words: None # string {'english'}, list, or None (default)
# min document frequency of a word to add to vocabulary
# float - the parameter represents a proportion of documents
# integer - absolute counts
min_df: 1 # float in range [0.0, 1.0] or int
# max document frequency of a word to add to vocabulary
# float - the parameter represents a proportion of documents
# integer - absolute counts
max_df: 1.0 # float in range [0.0, 1.0] or int
# set ngram range
min_ngram: 1 # int
max_ngram: 1 # int
# limit vocabulary size
max_features: None # int or None
# if convert all characters to lowercase
lowercase: true # bool
# handling Out-Of-Vacabulary (OOV) words
# will be converted to lowercase if lowercase is true
OOV_token: None # string or None
OOV_words: [] # list of strings
pipeline:
- name: "SklearnIntentClassifier"
# Specifies the list of regularization values to
# cross-validate over for C-SVM.
# This is used with the ``kernel`` hyperparameter in GridSearchCV.
C: [1, 2, 5, 10, 20, 100]
# Specifies the kernel to use with C-SVM.
# This is used with the ``C`` hyperparameter in GridSearchCV.
kernels: ["linear"]
defaults = {
# nn architecture
# sizes of hidden layers before the embedding layer for input words
# the number of hidden layers is thus equal to the length of this list
"hidden_layers_sizes_a": [256, 128],
# sizes of hidden layers before the embedding layer for intent labels
# the number of hidden layers is thus equal to the length of this list
"hidden_layers_sizes_b": [],
# Whether to share the hidden layer weights between input words and labels
"share_hidden_layers": False,
# training parameters
# initial and final batch sizes - batch size will be
# linearly increased for each epoch
"batch_size": [64, 256],
# how to create batches
"batch_strategy": "balanced", # string 'sequence' or 'balanced'
# number of epochs
"epochs": 300,
# set random seed to any int to get reproducible results
"random_seed": None,
# embedding parameters
# default dense dimension used if no dense features are present
"dense_dim": {"text": 512, "label": 20},
# dimension size of embedding vectors
"embed_dim": 20,
# the type of the similarity
"num_neg": 20,
# flag if minimize only maximum similarity over incorrect actions
"similarity_type": "auto", # string 'auto' or 'cosine' or 'inner'
# the type of the loss function
"loss_type": "softmax", # string 'softmax' or 'margin'
# how similar the algorithm should try
# to make embedding vectors for correct labels
"mu_pos": 0.8, # should be 0.0 < ... < 1.0 for 'cosine'
# maximum negative similarity for incorrect labels
"mu_neg": -0.4, # should be -1.0 < ... < 1.0 for 'cosine'
# flag: if true, only minimize the maximum similarity for incorrect labels
"use_max_sim_neg": True,
# scale loss inverse proportionally to confidence of correct prediction
"scale_loss": True,
# regularization parameters
# the scale of L2 regularization
"C2": 0.002,
# the scale of how critical the algorithm should be of minimizing the
# maximum similarity between embeddings of different labels
"C_emb": 0.8,
# dropout rate for rnn
"droprate": 0.2,
# visualization of accuracy
# how often to calculate training accuracy
"evaluate_every_num_epochs": 20, # small values may hurt performance
# how many examples to use for calculation of training accuracy
"evaluate_on_num_examples": 0, # large values may hurt performance
}
defaults = {
# nn architecture
# sizes of hidden layers before the embedding layer for input words
# the number of hidden layers is thus equal to the length of this list
"hidden_layers_sizes_a": [256, 128],
# sizes of hidden layers before the embedding layer for intent labels
# the number of hidden layers is thus equal to the length of this list
"hidden_layers_sizes_b": [256, 128],
# Whether to share the hidden layer weights between input words and intent labels
"share_hidden_layers": False,
# training parameters
# initial and final batch sizes - batch size will be
# linearly increased for each epoch
"batch_size": [64, 256],
# how to create batches
"batch_strategy": "balanced", # string 'sequence' or 'balanced'
# number of epochs
"epochs": 300,
# set random seed to any int to get reproducible results
"random_seed": None,
# embedding parameters
# default dense dimension used if no dense features are present
"dense_dim": {"text": 512, "label": 20},
# dimension size of embedding vectors
"embed_dim": 20,
# the type of the similarity
"num_neg": 20,
# flag if minimize only maximum similarity over incorrect actions
"similarity_type": "auto", # string 'auto' or 'cosine' or 'inner'
# the type of the loss function
"loss_type": "softmax", # string 'softmax' or 'margin'
# how similar the algorithm should try
# to make embedding vectors for correct intent labels
"mu_pos": 0.8, # should be 0.0 < ... < 1.0 for 'cosine'
# maximum negative similarity for incorrect intent labels
"mu_neg": -0.4, # should be -1.0 < ... < 1.0 for 'cosine'
# flag: if true, only minimize the maximum similarity for
# incorrect intent labels
"use_max_sim_neg": True,
# scale loss inverse proportionally to confidence of correct prediction
"scale_loss": True,
# regularization parameters
# the scale of L2 regularization
"C2": 0.002,
# the scale of how critical the algorithm should be of minimizing the
# maximum similarity between embeddings of different intent labels
"C_emb": 0.8,
# dropout rate for rnn
"droprate": 0.2,
# visualization of accuracy
# how often to calculate training accuracy
"evaluate_every_num_epochs": 20, # small values may hurt performance
# how many examples to use for calculation of training accuracy
"evaluate_on_num_examples": 0, # large values may hurt performance,
# selector config
# name of the intent for which this response selector is to be trained
"retrieval_intent": None,
}
其中retrieval_intent：设置训练此响应选择器模型的意图的名称。默认是None
Output-Example：
{
"text": "What is the recommend python version to install?",
"entities": [],
"intent": {"confidence": 0.6485910906220309, "name": "faq"},
"intent_ranking": [
{"confidence": 0.6485910906220309, "name": "faq"},
{"confidence": 0.1416153159565678, "name": "greet"}
],
"response_selector": {
"faq": {
"response": {"confidence": 0.7356462617, "name": "Supports 3.5, 3.6 and 3.7, recommended version is 3.6"},
"ranking": [
{"confidence": 0.7356462617, "name": "Supports 3.5, 3.6 and 3.7, recommended version is 3.6"},
{"confidence": 0.2134543431, "name": "You can ask me about how to get started"}
]
}
}
}
[{
"text": "I moved to New York City",
"intent": "inform_relocation",
"entities": [{"value": "nyc",
"start": 11,
"end": 24,
"entity": "city",
}]
},
{
"text": "I got a new flat in NYC.",
"intent": "inform_relocation",
"entities": [{"value": "nyc",
"start": 20,
"end": 23,
"entity": "city",
}]
}]
该组件将实体New York City和NYC映射到nyc。即使消息包含NYC，实体提取将返回nyc。当该组件更改现有实体时，它将自己附加到该实体的处理器列表中。
pipeline:
- name: "CRFEntityExtractor"
# The features are a ``[before, word, after]`` array with
# before, word, after holding keys about which
# features to use for each word, for example, ``"title"``
# in array before will have the feature
# "is the preceding word in title case?".
# Available features are:
# ``low``, ``title``, ``suffix5``, ``suffix3``, ``suffix2``,
# ``suffix1``, ``pos``, ``pos2``, ``prefix5``, ``prefix2``,
# ``bias``, ``upper``, ``digit``, ``pattern``, and ``text_dense_features``
features: [["low", "title"], ["bias", "suffix3"], ["upper", "pos", "pos2"]]
# The flag determines whether to use BILOU tagging or not. BILOU
# tagging is more rigorous however
# requires more examples per entity. Rule of thumb: use only
# if more than 100 examples per entity.
BILOU_flag: true
# This is the value given to sklearn_crfcuite.CRF tagger before training.
max_iterations: 50
# This is the value given to sklearn_crfcuite.CRF tagger before training.
# Specifies the L1 regularization coefficient.
L1_c: 0.1
# This is the value given to sklearn_crfcuite.CRF tagger before training.
# Specifies the L2 regularization coefficient.
L2_c: 0.1
为了使用该组件需要启动一个duckling server。最简单的选择是使用docker container：docker run -p 8000:8000 rasa/duckling。另外，也可以直接在机器上安装Duckling再启动服务。Duckling可以识别日期、数字、距离和其他结构化实体和规范。请注意,duckling 试图提取尽可能多的实体类型，但没有提供排名。例如，对于文本I will be there in 10 minutes。如果在duckling组件内同时指定number和time维度,则该组件将提取两个实体：10作为数字和10 minutes作为时间。在这种情况下,应用程序必须决定哪些实体类型是正确的。抽取器将始终返回1.0的置信度,因为这是一个基于规则的系统。
pipeline:
- name: "DucklingHTTPExtractor"
# url of the running duckling server
url: "http://localhost:8000"
# dimensions to extract
dimensions: ["time", "number", "amount-of-money", "distance"]
# allows you to configure the locale, by default the language is
# used
locale: "de_DE"
# if not set the default timezone of Duckling is going to be used
# needed to calculate dates from relative expressions like "tomorrow"
timezone: "Europe/Berlin"
# Timeout for receiving response from http url of the running duckling server
# if not set the default timeout of duckling http url is set to 3 seconds.
timeout : 3
扫一扫
455
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
