All Projects → rainarch → Sentibridge

rainarch / Sentibridge

Licence: other
SentiBridge: A Knowledge Base for Entity-Sentiment Representation

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Sentibridge

Cluedatasetsearch
搜索所有中文NLP数据集,附常用英文NLP数据集
Stars: ✭ 2,112 (+289.67%)
Mutual labels:  knowledge-graph, sentiment-analysis
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 (+45.94%)
Mutual labels:  knowledge-graph, sentiment-analysis
Athens
Free self-hosted desktop app: https://github.com/athensresearch/athens/releases; Try the demo at https://athensresearch.github.io/athens; Docs viewable at https://athensresearch.github.io/docs/
Stars: ✭ 5,501 (+914.94%)
Mutual labels:  knowledge-graph
Rust Bert
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Stars: ✭ 510 (-5.9%)
Mutual labels:  sentiment-analysis
Ripplenet
A tensorflow implementation of RippleNet
Stars: ✭ 434 (-19.93%)
Mutual labels:  knowledge-graph
Gnn4nlp Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
Stars: ✭ 405 (-25.28%)
Mutual labels:  knowledge-graph
Nlp.js
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
Stars: ✭ 4,670 (+761.62%)
Mutual labels:  sentiment-analysis
Awesome Knowledge Graph
A curated list of Knowledge Graph related learning materials, databases, tools and other resources
Stars: ✭ 382 (-29.52%)
Mutual labels:  knowledge-graph
Awesome Twitter Data
A list of Twitter datasets and related resources.
Stars: ✭ 533 (-1.66%)
Mutual labels:  sentiment-analysis
Weibo Analyst
Social media (Weibo) comments analyzing toolbox in Chinese 微博评论分析工具, 实现功能: 1.微博评论数据爬取; 2.分词与关键词提取; 3.词云与词频统计; 4.情感分析; 5.主题聚类
Stars: ✭ 430 (-20.66%)
Mutual labels:  sentiment-analysis
Atomspace
The OpenCog (hyper-)graph database and graph rewriting system
Stars: ✭ 495 (-8.67%)
Mutual labels:  knowledge-graph
Deep Learning V2 Pytorch
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Stars: ✭ 4,457 (+722.32%)
Mutual labels:  sentiment-analysis
Kglib
Grakn Knowledge Graph Library (ML R&D)
Stars: ✭ 405 (-25.28%)
Mutual labels:  knowledge-graph
Awesome Sentiment Analysis
Repository with all what is necessary for sentiment analysis and related areas
Stars: ✭ 459 (-15.31%)
Mutual labels:  sentiment-analysis
Deeppath
code and docs for my EMNLP paper "DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning"
Stars: ✭ 398 (-26.57%)
Mutual labels:  knowledge-graph
Knowledge Graph Learning
A curated list of awesome knowledge graph tutorials, projects and communities.
Stars: ✭ 516 (-4.8%)
Mutual labels:  knowledge-graph
Dynamic Kg
Dynamic (Temporal) Knowledge Graph Completion (Reasoning)
Stars: ✭ 381 (-29.7%)
Mutual labels:  knowledge-graph
Geistmap
An experimental personal knowledge base with a focus on connections
Stars: ✭ 425 (-21.59%)
Mutual labels:  knowledge-graph
Lightkg
基于Pytorch和torchtext的知识图谱深度学习框架。
Stars: ✭ 452 (-16.61%)
Mutual labels:  knowledge-graph
Sentiment Analysis In Event Driven Stock Price Movement Prediction
Use NLP to predict stock price movement associated with news
Stars: ✭ 540 (-0.37%)
Mutual labels:  sentiment-analysis

SentiBridge

《SentiBridge: 中文实体情感知识库》/ SentiBridge: A Knowledge Base for Entity-Sentiment Representation

本词典包含:实体/属性—情感词。例如:“长城 宏伟”、“性价比 高”、“价格 高”。主要目的是刻画人们是怎么描述某个实体的,例如大家通常用 宏伟 来形容长城。

目前词典包含三个领域语料的抽取结果:新闻、旅游、餐饮,共计30万对。

文件说明(SentiBridge.zip)

每个文件夹中包含两种文件

  1. 前缀pair_sort代表排序得到的结果:
  • pair_sort_[m,n],指的是从m%到n%的排序部分

  • 数据形式是:实体/属性 情感词 收敛分数

  1. 前缀pair_mine代表提炼得到的结果:
  • 数据形式是:实体/属性 情感词 相似度分数1 相似度分数2

  • pair_mine后面的数字是提炼算法得到的结果中,保证正确率取的分数值。即文本中所有分数1和2,都必须高于该值并保留的结果

领域说明

  1. 新闻领域(Gigaword新闻语料):
  • pair_sort_[0,1],正确率统计92%,数量11.9w个
  • pair_mine_0.25,正确率统计90%,数量1.7w个
  1. 旅游领域(旅游用户评论):
  • pair_sort_[0,1],正确率统计98%
  • pair_sort_[1,2],正确率统计94%
  • pair_sort_[2,3],正确率统计90%
  • 以上总计8w个
  • pair_mine_0.2,正确率统计90%,数量5624个
  1. 餐饮领域(餐饮用户评论):
  • pair_sort_[0,1],正确率统计92%,数量9.3w个
  • pair_mine_0.2,正确率统计90%,数量5.2w个

代码

  • 代码在目录: ./Entity_Emotion_Express
  • 为了取得较好效果,最好使用用户评论数据,例如:淘宝评论、大众点评评论、携程评论等等。

声明和参考文献

  1. SentiBridge数据仅供学术研究使用,商用请联系我们(wlchen at suda.edu.cn)获取授权。
  2. 相关文献
  • 卢奇, 陈文亮. 大规模中文实体情感知识的自动获取, 中文信息学报, 32 (8): 32-41, 2018年8月
  • LU Qi, CHEN Wenliang, Automatically Building a Large Scale Dictionary of Chinese Entity Sentiment Expressions, Journal of Chinese Information Processing, 32 (8): 32-41, 2018-8.
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].