- CSTS: 中文自然语言推理与语义相似度数据集
- CLUE文本相似度任务: SimCLUE
- 千言文本相似度任务
- CNSD:中文自然语言推理数据集
- 搜索中的深度匹配模型·上，搜索中的深度匹配模型·下
- 文本相似度/文本匹配模型归纳总结
- 竞赛中的文本相似性！
- 知乎搜索排序模型的演进
- 阿里飞猪搜索技术的应用与创新
- 阿里粗排技术体系与最新进展
- 图谱实战 | 阿里周晓欢：如何将实体抽取从生成问题变成匹配问题？
- 丁香园：聊聊电商搜索的语义理解问题/从文本匹配到语义相关——新闻相似度计算的一般思路
- 都是推荐系统，广告算法和推荐算法有啥区别？
- 初来乍到：帮助新用户冷启的算法技巧
- KG与搜广推入门：C端广告业务的生态、展示类型、结算方式与评估指标总结
- 21个经典深度学习句间关系模型｜代码&技巧, 交互模型你快跑，双塔要卷过来了
- 两万字聊对话系统
- 一文详解文本语义相似度的研究脉络和最新进展
- 搜狐文本匹配算法大赛方案总结
- 京东推荐算法精排技术实践
- 综述 | 《面向推荐的大型语言模型》
- When RS Meets LLM：推荐系统如何从大语言模型中取长补短？面向应用视角的全面综述
- 大模型实现生成式推荐系统
- 写了个向量检索的baseline
- 无监督字面相似度CQR/CTR源码
- Model Collections
- deep-text-matching: implementation several deep text match (text similarly) models for keras . cdssm, arc-ii,match_pyramid, mvlstm ,esim, drcn ,bimpm, bert, albert, raberta.
- text_matching: Models such as DSSM, ESIM, ABCNN, BiMPM.
- tensorflow-DSMM: Tensorflow implementations of various Deep Semantic Matching Models (DSMM).
- semantic-matching: semantic matching/text matching models including MatchPyramid, MV-LSTM, ABCNN.
- Text-Similarity: Text-Similarity Method in Pytorch for ESIM, SiaGRU, ABCNN, BiMPM.
- TextSimilar: MatchPyramid, Siamese RNN.
- DSSM
- ARC-I & ARC-II
- MatchPyramid
- paper: Text Matching as Image Recognition
- code: tensorflow ver., keras ver., pytorch ver., unofficial
- MV-LSTM
- paper: A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
- code: tensorflow ver., unofficial
- aNMM
- ABCNN
- HCRN
- paper: Hermitian Co-Attention Networks for Text Matching in Asymmetrical Domains
- BiMPM
- paper: Bilateral Multi-Perspective Matching for Natural Language Sentences
- ESIM
- paper: Enhanced LSTM for Natural Language Inference
- code: tensorflow ver., keras ver., keras ver.2, pytorch ver., Theano ver.
- DIIN
- RE2
- DSI
- paper: Transformer Memory as a Differentiable Search Index (DSI, 可微搜索索引)
- further reading
- SDEs vs ADEs
- paper: Exploring Dual Encoder Architectures for Question Answering
- further reading
- Trans-Encoder
- ann-benchmarks: a benchmarking environment for approximate nearest neighbor algorithms search.
- faiss
- SPTAG
- milvus
- vearch
- jina
- blog:
- LibRerank: a toolkit for re-ranking algorithms, such as PRM, DLCM, GSF, miDNN, SetRank, EGRerank, Seq2Slate.
- Blogs:
- SimCSE
- paper: SimCSE: Simple Contrastive Learning of Sentence Embeddings
- code
- demo
- introduction blog
- further reading
- R-Drop: 又是Dropout两次！这次它做到了有监督任务的SOTA
- Chinese SimCSE
- code
- further reading
- ConSERT
- SimCTG
- PyGCL
- code
- note: an open-source Graph Contrastive Learning (GCL) library for PyTorch
- PairSCL
- SNCSE
- DualCL
- paper: Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
- further reading
- PICO
- Open-world Contrastive Learning
- SimBERT
- blog: 鱼与熊掌兼得：融合检索和生成的SimBERT模型
- code
- ERNIE-Gram
- CoSENT
- BERT-whitening
- idea(blog): 你可能不需要BERT-flow：一个线性变换媲美BERT-flow
- experiments(blog): 无监督语义相似度哪家强？我们做了个比较全面的评测
- paper
- blog 当BERT-whitening引入超参数：总有一款适合你
- Perfect Match
- PT-HCL