All Projects → ownthink → Semantic

ownthink / Semantic

语义理解/口语理解,项目包含有词法分析:中文分词、词性标注、命名实体识别;口语理解:领域分类、槽填充、意图识别。

Programming Languages

python
139335 projects - #7 most used programming language

Labels

Projects that are alternatives of or similar to Semantic

Rasa Ui
Rasa UI is a frontend for the Rasa Framework
Stars: ✭ 796 (+452.78%)
Mutual labels:  nlu
Botpress
🤖 Dev tools to reliably understand text and automate conversations. Built-in NLU. Connect & deploy on any messaging channel (Slack, MS Teams, website, Telegram, etc).
Stars: ✭ 9,486 (+6487.5%)
Mutual labels:  nlu
Delta
DELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+927.08%)
Mutual labels:  nlu
Pytlas
An open-source 🤖💬 Python 3 assistant library built for people and made to be super easy to setup and understand
Stars: ✭ 34 (-76.39%)
Mutual labels:  nlu
Atis dataset
The ATIS (Airline Travel Information System) Dataset
Stars: ✭ 81 (-43.75%)
Mutual labels:  nlu
Duckling old
Deprecated in favor of https://github.com/facebook/duckling
Stars: ✭ 1,332 (+825%)
Mutual labels:  nlu
Tc Bot
User Simulation for Task-Completion Dialogues
Stars: ✭ 733 (+409.03%)
Mutual labels:  nlu
Rasa
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Stars: ✭ 13,219 (+9079.86%)
Mutual labels:  nlu
Spark Nlp Models
Models and Pipelines for the Spark NLP library
Stars: ✭ 88 (-38.89%)
Mutual labels:  nlu
Spokestack Python
Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application.
Stars: ✭ 103 (-28.47%)
Mutual labels:  nlu
Easynlu
Simple embedded NLU for mobile apps
Stars: ✭ 57 (-60.42%)
Mutual labels:  nlu
Cherubnlp
Natural Language Processing in .NET Core
Stars: ✭ 71 (-50.69%)
Mutual labels:  nlu
Botfuel Dialog
Botfuel SDK to build highly conversational chatbots
Stars: ✭ 96 (-33.33%)
Mutual labels:  nlu
Crosslingual Nlu
Zero-shot Cross-lingual Task-Oriented Dialogue Systems (EMNLP 2019)
Stars: ✭ 20 (-86.11%)
Mutual labels:  nlu
Nlp Papers
Papers and Book to look at when starting NLP 📚
Stars: ✭ 111 (-22.92%)
Mutual labels:  nlu
Chatbot cn
基于金融-司法领域(兼有闲聊性质)的聊天机器人,其中的主要模块有信息抽取、NLU、NLG、知识图谱等,并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口
Stars: ✭ 791 (+449.31%)
Mutual labels:  nlu
Tracy
A simple and easy to use trainer to generate Rasa/Snips NLU datasets
Stars: ✭ 92 (-36.11%)
Mutual labels:  nlu
Clue
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Stars: ✭ 2,425 (+1584.03%)
Mutual labels:  nlu
Awesome Hungarian Nlp
A curated list of NLP resources for Hungarian
Stars: ✭ 121 (-15.97%)
Mutual labels:  nlu
Chinese nlu by using rasa nlu
使用 RASA NLU 来构建中文自然语言理解系统(NLU)| Use RASA NLU to build a Chinese Natural Language Understanding System (NLU)
Stars: ✭ 99 (-31.25%)
Mutual labels:  nlu

语义理解/口语理解

采用了深度学习等技术

主要功能:

  • 中文分词
  • 词性标注
  • 命名实体识别
  • 领域分类
  • 槽填充
  • 意图识别

自然语言处理使用的是作者开源的Jiagu项目:https://github.com/ownthink/Jiagu

spoken举例:

上海的天气
厦门明天会不会下雨
姚明真正的身高是多少

使用方式

python3 test.py

解析结果

{
    "input": "厦门明天会不会下雨", 
    "semantics": [
        {
            "score": "0.8", 
            "domain": "天气", 
            "intent": "雨", 
            "slot": [
                [
                    "城市", 
                    "厦门"
                ], 
                [
                    "日期", 
                    "明天"
                ]
            ]
        }
    ], 
    "词法分析": {
        "词性标注": [
            "地名", 
            "时间词", 
            "动词", 
            "动词", 
            "动词"
        ], 
        "实体识别": [
            "B-地名", 
            "O", 
            "O", 
            "O", 
            "O"
        ], 
        "中文分词": [
            "厦门", 
            "明天", 
            "会", 
            "不会", 
            "下雨"
        ]
    }
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].