The famous, classic and latest development of the ranking model in search, recommendation, and advertising. Mainly about CTR, CVR and other ranking model etc.
I try to classify each work carefully, but the mistake are inevitable because there are lots of overlaps in different field. Like the ctr and ranking or query-doc similarity are similar. Hope this is helpful for you and me. We find a special road-map for learning from this repo. If you find any mistake, please don't hesitate to issue or pr. Thank you very much.
- Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm, arXiv2021
- Deep Learning for Click-Through Rate Estimation, IJCAI2021
- Pretrained Transformers for Text Ranking: BERT and Beyond, Synthesis Lectures on Human Language Technologies, 2021
- Ad Click-Through Rate Prediction: A Survey, International Conference on Database Systems for Advanced Applications, 2021
- DIN, Deep interest network for click-through rate prediction, SIGKDD2018,
- MTRUB, Multi-task Ranking with User Behaviors for Text-video Search, WWW2022,
- K-NRM, End-to-End Neural Ad-hoc Ranking with Kernel Pooling, SIGIR2017, [word-based, kernel pooling, soft match], code-pytorch, code-tf
-
MatchPyramid, Text Matching as Image Recognition, AAAI2016, classic, [word-based conv], code-pytorch
-
Local-distributed model, Learning to match using local and distributed representations of text for web search, WWW2017,
-
Enhanced-LSTM, Enhanced LSTM for natural language inference, ACL2017, offical-code-Theano, code-keras
-
Conv-KNRM, Convolutional Neural Networks for Soft-Matching N-Grams in Ad-hoc Search, WSDM2018,
-
Sentence-matching, Semantic sentence matching with densely-connected recurrent and co-attentive information, AAAI2019,
-
Emb-based retrieval, Embedding-based retrieval in facebook search, SIGKDD2020,
-
MASM, Learning a Product Relevance Model from Click-Through Data in E-Commerce, WWW2021
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent