一、經典論文
nlp：
| 描述 | 論文 |
| deep learning for nlp的早期框架 | A unified architecture for natural language processing: deep neural networks with multitask learning |
| 主題模型：LDA | Latent dirichlet allocation |
| 條件隨機場： | Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data |
| word2vec | Efficient Estimation of Word Representations in Vector Space |
| glove | Glove: Global Vectors for Word Representation |
| elmo | https://arxiv.org/pdf/1802.05365.pdfDeep contextualized word representations |
| nlp中的cnn | Convolutional Neural Networks for Sentence Classification |
| RNN-based seq2seq | Sequence to Sequence Learning with Neural Networks Neural Machine Translation by Jointly Learning to Align and Translate |
| Attention is all you need （絕對經典） | Attention Is All You Need |
| Bert （重點） | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding |
| transformer-XL | Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context - arXiv 2019) |
| 長文本transformer | Longformer: The Long-Document Transformer |
| bert壓縮 | TinyBERT: Distilling BERT for Natural Language Understanding DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter ALBERT: A Lite BERT for Self-supervised Learning of Language Representations |
| 融入知識圖譜資訊 | K-BERT: Enabling Language Representation with Knowledge Graph https://arxiv.org/pdf/1909.07606.pdf ERNIE: Enhanced Representation through Knowledge Integration https://arxiv.org/pdf/1904.09223.pdf |
推薦演算法：
[Youtube-DNN] Deep Neural Networks for YouTube Recommendations（Google 2016，非常經典的論文）
[Pinterest] Graph Convolutional Neural Networks for Web-Scale Recommender Systems (Pinterest 2018)
[DL Recsys Intro] Deep Learning based Recommender System- A Survey and New Perspectives (UNSW 2018)
召回：
[DSSM雙塔模型] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)
[TDM] Learning Tree-based Deep Model for Recommender Systems（Alibaba 2018）
排序：
[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018，多任務)
[MMOE] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts（Google 2018，眾多大廠都有用這個模型，多任務）
[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)
[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)
其它：
[tutorial] Learning to Rank for Information Retrieval（Microsoft 2010，劉鐵巖經典綜述）
[DeepWalk] DeepWalk: Online Learning of Social Representations（2014）
[item2vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016)
[node2vec] node2vec: Scalable Feature Learning for Networks（2016）
二、近年新論文
nlp：
| 描述 | 論文 |
| 小樣本 | Multi-Label Few-Shot Learning for Aspect Category Detection https://arxiv.org/abs/2105.1417 Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision https://arxiv.org/abs/2012.1486 Generalizing from a Few Examples: A Survey on Few-Shot Learning（小樣本學習綜述） |
| NER | Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data https://arxiv.org/abs/2106.0897 Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker https://arxiv.org/abs/2105.1492 |
| 對話 | Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction https://arxiv.org/abs/2011.1313 |
| 生成 | Prefix-Tuning: Optimizing Continuous Prompts for Generation https://arxiv.org/abs/2101.0019 |
| 摘要 | Cross-Lingual Abstractive Summarization with Limited Parallel Resources https://arxiv.org/abs/2105.1364 Long-Span Summarization via Local Attention and Content Selection https://arxiv.org/abs/2105.0380 |
| 預訓練模型 | Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling NEZHA: Neural Contextualized Representation for Chinese Language Understanding ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language ERNIE 2.0: A Continual Pre-training Framework for Language Understanding |
| 表征學習 | DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations https://arxiv.org/abs/2006.03659（對比學習） ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer https://arxiv.org/abs/2105.1174 Self-Guided Contrastive Learning for BERT Sentence Representations https://arxiv.org/abs/2106.0734 |
| 知識圖譜 | Dynamic Knowledge Graph Construction for Zero-shot Commonsense Question Answering Case-based Reasoning for Natural Language Queries over Knowledge Bases https://arxiv.org/pdf/2104.08762.pdf Dynamic Knowledge Graph Construction for Zero-shot Commonsense Question Answering |
推薦演算法：
[Graph learning] Graph Learning Approaches to Recommender Systems: A Review（2021）
召回：
[JTM] Joint Optimization of Tree-based Index and Deep Model for Recommender Systems（Alibaba 2019）
[Deep Retrieval] Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations（位元組 2021）
排序：
[PLE] Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations（騰訊 2020，近一年很多大廠有follow這項作業，多任務）
其它：
[KAFtt] Kalman Filtering Attention for User Behavior Modeling in CTR Prediction（京東 2020）
[SIM] Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction （Alibaba 2020）
[BST] Behavior Sequence Transformer for E-commerce Recommendation in Alibaba（Alibaba 2019）
[GIN] Graph Intention Network for Click-through Rate Prediction in Sponsored Search（Alibaba 2019）
三、知識點重難點解讀
nlp：
Prompt Based Task Reformulation in NLP調研 | Thinkwee's Blog
https://github.com/km1994/nlp_paper_study
GitHub - km1994/NLP-Interview-Notes: 本專案是作者們根據個人面試和經驗總結出的自然語言處理(NLP)面試準備的學習筆記與資料，該資料目前包含 自然語言處理各領域的 面試題積累，
推薦演算法：
GitHub - shenweichen/AlgoNotes: 公眾號【淺夢學習筆記】文章匯總:包含 排序&CXR預估，召回匹配，用戶畫像&特征工程，推薦搜索綜合 計算廣告，大資料，圖演算法，NLP&CV，求職面試 等內容
GitHub - datawhalechina/fun-rec: 本推薦演算法教程主要是針對具有機器學習基礎并想找推薦演算法崗位的同學，教程由推薦演算法基礎、推薦演算法入門賽、新聞推薦專案及推薦演算法面經組成，形成了一個完整的從基礎到實戰再到面試的倍訓，
四、面經系列
快手推薦演算法實習面經_筆經面經_牛客網
社招一年：小米演算法面經(推薦演算法)_筆經面經_牛客網
美團推薦演算法暑期實習崗面經_筆經面經_牛客網
秋招總結：非機器學習科班學生漫長的演算法工程師上岸之旅_筆經面經_牛客網
演算法崗秋招面經總結，回饋牛客_筆經面經_牛客網
某渣渣NLP暑期實習面經_筆經面經_牛客網
NLP面經回饋_筆經面經_牛客網
NLP and 機器學習面經，回饋牛客_筆經面經_牛客網
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/429284.html
標籤：AI
上一篇：Fast-R-CNN論文解讀