PMI, 是互信息(NMI)中的一种特例, 而互信息,是源于信息论中的一个概念,主要用于衡量2个信号的关联程度.至于PMI,是在文本处理中,用于计算两个词语之间的关联程度.比起传统的相似度计算, pmi的好处在于,从统计的角度发现词语共现的情况来分析出词语间是否存在语义相关 , 或者主题相关的情况.
☆15Aug 24, 2020Updated 5 years ago
Alternatives and similar repositories for PMI
Users that are interested in PMI are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 为提高推理速度优化代码，并在中文语料上复现RE2模型☆15Mar 24, 2023Updated 3 years ago
- 基于NER的文本纠错☆15Dec 27, 2023Updated 2 years ago
- 基于bert进行中文文本纠错☆242Jun 12, 2023Updated 2 years ago
- ☆25Mar 6, 2016Updated 10 years ago
- 中文错别字纠正工具。音似、形似错字（或变体字）纠正，可用于中文拼音、笔画输入法的错误纠正。python开发。☆10Mar 5, 2018Updated 8 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Something Temporary☆10Oct 18, 2018Updated 7 years ago
- Modify Chinese text, modified on LaserTagger Model. 文本复述，基于lasertagger做中文文本数据增强。☆322Jan 3, 2024Updated 2 years ago
- A simple implementation of Transformer Encoder in keras. This repository also includes an example of Transformer as a classifier and its …☆16Apr 9, 2019Updated 7 years ago
- Code for NLPCC2016 Chinese Word Similarity Task☆17Sep 8, 2016Updated 9 years ago
- 使用gensim训练word2vec模型并对训练得到词向量聚类☆16Sep 23, 2017Updated 8 years ago
- 【Demo】找寻近义词的三种方法☆27Sep 21, 2020Updated 5 years ago
- ☆22Jul 2, 2021Updated 4 years ago
- 问题等价性判断数据预处理，包含添加对抗样本（同音字、近义词替换等）、获取样本的pattern（用通配符替换相同词汇，提取相同和不同词汇）☆39Dec 23, 2019Updated 6 years ago
- ☆15Sep 2, 2017Updated 8 years ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆31Sep 6, 2023Updated 2 years ago
- Hermes is a library built on top of TensorFlow 2 designed to provide simple, abstractions for natural language processing utilizing end t…☆18Jun 5, 2021Updated 4 years ago
- Code for the paper "VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis", AAAI'19☆89Apr 1, 2023Updated 3 years ago
- My implementation of 《Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory》☆34Oct 15, 2019Updated 6 years ago
- 新词发现算法与同义词挖掘☆27Oct 24, 2017Updated 8 years ago
- 中文领域的多模态Bert☆46Mar 24, 2020Updated 6 years ago
- 电商评论观点挖掘☆45Jan 29, 2021Updated 5 years ago
- 简易的中文纠错和消歧☆289Aug 19, 2015Updated 10 years ago
- ☆22Sep 3, 2018Updated 7 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- JDDC基线模型Seq2Seq☆39May 8, 2018Updated 7 years ago
- Cloud Native Distributed Nearest Neighbour Search☆15Jun 9, 2020Updated 5 years ago
- (TensorFlow) Sequence to sequence with attention model, emotion regressor, and Emotional Chatting Machine.☆42Jul 4, 2018Updated 7 years ago
- 利用bert预训练模型生成句向量或词向量☆26Oct 29, 2020Updated 5 years ago
- This repository contains PyTorch implementations of the models from the paper An Empirical Study MIME: MIMicking Emotions for Empathetic …☆46Mar 14, 2023Updated 3 years ago
- Package vecf32 provides common functions and methods for slices of float32☆13Jun 14, 2023Updated 2 years ago
- Repository for Skill Set Optimization☆14Jul 26, 2024Updated last year
- Code for EMNLP 2019 paper "A Boundary-aware Neural Model for Nested Named Entity Recognition"☆89Jan 24, 2022Updated 4 years ago
- Codebase for Efficient yet simple Reinforcement Learning Research Framework☆28Jan 14, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Notebooks for docarray, Jina, Finetuner, and other products from Jina AI☆12Mar 31, 2022Updated 4 years ago
- mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models☆11Jan 19, 2024Updated 2 years ago
- 依据香港中文大学设计的规则系统，先用小样本评论建立初始关键词库，再结合18种句式逐条匹配评论，能够快速准确地识别评论对象及情感极性。经多次迭代优化关键词库后，达到较高准确率的基础上，使用Tableau进一步分析数据，识别出客户集中关注的商品属性、普遍好评差评的商品属性；通过…☆57Sep 19, 2017Updated 8 years ago
- TSDG: An efficient index graph for graph-based nearest neighbor search☆10Jul 14, 2022Updated 3 years ago
- Latent Large Language Models☆19Aug 24, 2024Updated last year
- A PyTorch implementation of Proxy Anchor Loss based on CVPR 2020 paper "Proxy Anchor Loss for Deep Metric Learning"☆11Jan 16, 2021Updated 5 years ago
- Server wrapper for ml models☆11Sep 11, 2019Updated 6 years ago