This book was co-authored by Synonyms authors.
Quick book purchase link
"Intelligent Question Answering and Deep Learning" This book is for students and software engineers who are preparing to get started with machine learning and natural language processing. It introduces many principles and algorithms in theory, and also provides many example programs to increase practicality. They are summarized in the sample program code library. These programs are mainly to help everyone understand the principles and algorithms. You are welcome to download and execute them. The address of the code base is:
https://github.com/l11x0m7/book-of-qna-code
Chinese Synonyms for Natural Language Processing and Understanding.
The best Chinese synonym toolkit.
synonyms
can be used for many tasks in natural language understanding: text alignment, recommendation algorithms, similarity calculations, semantic offset, keyword extraction, concept extraction, automatic summarization, search engines, etc.
npm install node-synonyms
This project is the Node.js toolkit of Synonyms. The stable version is v1. It has been tested under Mac OSX and Linux . Currently, after packaging, the npm module is 47MB. This is because the vocabulary file is very large, so you need to be patient when downloading.
Supports the use of environment variable configuration:
environment variables | describe | default value |
---|---|---|
SYN_MODEL_W2V_PATH | Word vector file obtained after word2vec training | node_modules/node-synonyms/data/words.vector |
SYN_WORDSEG_CUSTOM_DICT | Word Segmentation User Dictionary | node_modules/node-synonyms/data/tokenizer/user.dict.utf8 |
SYN_WORDSEG_STOPWORD_DICT | word segmentation stop word dictionary | node_modules/node-synonyms/data/tokenizer/stop_words.utf8 |
SYN_WORDSEG_PUNCT_DICT | Word segmentation punctuation dictionary | node_modules/node-synonyms/data/tokenizer/punctuation.utf8 |
var synonyms = require("node-synonyms") # 使用上述环境变量做定制化
All interface return values are Promise.
word segmentation interface
let sen1 = "移动互联网";
synonyms.seg(sen1, true, true)
.then(function(words){
// do your magic
});
stopwords (Boolean) whether to retain stop words, punct (Boolean) whether to retain punctuation marks.
[String], a list of words.
["移动","互联网"]
Returns a vector of words
synonyms.vector("股市")
.then(function(v){
// do your magic
})
[float]
, a vector of 100-dimensional float values.
Print the neighbors and relevance of a word
synonyms.display("飞机");
Returns the neighbors of a word
synonyms.nearby("股市")
.then(function(results){
// do your magic
});
[[words], [scores]]
, contains two lists, the first is the word, the second is the distance score of the corresponding word, also in the [0~1] interval, the closer to 1 the more similar it is.
for example:
[
["股市","股价","股票市场","股灾","楼市","股票","香港股市","行情","恒指","金融市场"],
[1,0.786284,0.784575,0.751607,0.712255,0.712179,0.710806,0.694434,0.67501,0.666439]
]
Compare two sentences for similarity
let sen1 = "移动互联网";
let sen2 = "互联网";
synonyms.compare(sen1, sen2)
.then(function(similarity){
// do your magic
});
The similarity is a float value in the confidence interval [0~1]. The closer it is to 1, the more similar it is.
admin/test.sh # 单元测试
nodejieba
fast-levenshtein
compute-cosine-distance
node-word2vec-reader
Synonyms publishes certificate GPL3.0. Data and procedures may be used in research and commercial products and must be cited and addressed, such as in any media, journals, magazines or blogs published.
@online{Synonyms:hain2017,
author = {Hai Liang Wang, Hu Ying Xi},
title = {中文近义词工具包Synonyms},
year = 2017,
url = {https://github.com/huyingxi/Synonyms},
urldate = {2017-09-27}
}
https://bot.chatopera.com/
Chatopera cloud service is a one-stop cloud service for implementing chat robots, and is billed based on the number of interface calls. Chatopera Cloud Service is a software-as-a-service instance of the Chatopera bot platform. Based on cloud computing, Chatopera cloud service is a chatbot-as-a-service cloud service.
The Chatopera robot platform includes components such as knowledge base, multi-round dialogue, intent recognition and speech recognition, standardized chat robot development, and supports scenarios such as enterprise OA intelligent Q&A, HR intelligent Q&A, intelligent customer service and online marketing. Enterprise IT departments and business departments use Chatopera cloud services to quickly bring chatbots online!
Custom dictionary
Custom terms
Create intent
Add arguments and slots
Training model
test conversation
Robot portrait
System integration
Chat history
Use now