本项目是揣摩研习社整理的论文阅读列表，我们关注自然语言处理、信息检索、多模态检索与理解等多个人工智能前沿领域。
我们每周会阅读分享最新的顶会文章。点击揣摩工作查看本社社员发表的顶会文章。
【对话生成】 【文本检索】 【多模态检索】 【因果推断】 【文本生成】 【信息抽取】 【揣摩工作】 【其他】
-
(ACL 2021) BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data. [Video] [PPT]
-
(ACL 2021) Dialogue Response Selection with Hierarchical Curriculum Learning. [Video][PPT]
-
(ACL 2020) Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks [Video] [PPT]
-
(ACL 2021) Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training [Video] [PPT]
-
(ACL 2022) PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation [Video] [PPT]
-
(EMNLP 2020) Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness [Video] [PPT]
-
(EMNLP 2020) Regularizing Dialogue Generation by Imitating Implicit Scenarios [Video] [PPT]
-
(SIGIR 2021) Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots [Video] [PPT]
-
(ACL 2022) Beyond Goldfish Memory: Long-Term Open-Domain Conversation [Video] [PPT]
-
(ACL 2020) Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation [Video] [PPT]
-
(ACL 2022) A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation [Video] [PPT]
-
(AAAI 2022) Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge [Video] [PPT]
-
(EMNLP 2021) Simple Entity-Centric Questions Challenge Dense Retrievers [Video] [PPT]
-
(ACL 2021) Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP [Video] [PPT]
-
(SIGIR 2021) Optimizing Dense Retrieval Model Training with Hard Negatives [Video] [PPT]
-
(NeurIPS 2021) BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models [Video] [PPT]
-
(ACL 2022) Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data [Video] [PPT]
-
(ACL 2021) Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrieval [Video] [PPT]
-
(SIGIR 2021) Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling [Video] [PPT]
-
(ICLR 2021) Adversarial Retriever-Ranker for Dense Text Retrieval [Video] [PPT]
-
(EMNLP 2021) Condenser: a Pre-training Architecture for Dense Retrieval [Video] [PPT]
-
[SIGIR-Forum] Rethinking Search: Making Domain Experts out of Dilettantes [Video] [PPT]
-
(EMNLP 2021) Learning with Instance Bundles for Reading Comprehension [Video] [PPT]
-
(ACL 2022) Simulating Bandit Learning from User Feedback for Extractive Question Answering [Video] [PPT]
-
(ACL 2022) Hey AI, Can You Solve Complex Tasks by Talking to Agents? [Video] [PPT]
-
(ACL 2022) Perceiving the World: Question-guided Reinforcement Learning for Text-based Games [Video] [PPT]
-
(ACL 2021) Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction [Video] [PPT]
-
(ACL 2022) Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework [Video] [PPT]
-
(ACL 2022) Multi-View Document Representation Learning for Open-Domain Dense Retrieval [Video] [PPT]
-
(Arxiv) Training Language Models with Memory Augmentation [PPT]
-
(SIGIR 2022) LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback [Video] [PPT]
-
(Arxiv) VIRT: Improving Representation-based Models for Text Matchingthrough Virtual Interaction [Video] [PPT]
-
(ACL 2022) Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents [Video] [PPT]
-
(ICLR 2022) P-ADAPTERS Robustly Extracting Factual Information from Language Models with Diverse Prompts [Video] [PPT]
-
(ACL 2022) Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations [Video] [PPT]
-
(SIGIR 2021) Dynamic Modality Interaction Modeling for Image-Text Retrieval [Video] [PPT]
-
(ACL 2021) VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words [Video] [PPT]
-
(CVPR 2022) Balanced Multimodal Learning via On-the-fly Gradient Modulation [Video] [PPT]
-
(ACM MM 2021) CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval [Video] [PPT]
-
(ICML 2022) Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks [Video] [PPT]
-
(ICCV 2021) Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query [Video] [PPT]
-
(SIGIR 2022) Modality-Balanced Embedding for Video Retrieval [Video] [PPT]
-
(NeurIPS 2021) Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [Video] [PPT]
-
(NAACL 2022) MCSE: Multimodal Contrastive Learning of Sentence Embeddings [Video] [PPT]
-
(CVPR 2021) Counterfactual VQA: A Cause-Effect Look at Language Bias [Video] [PPT]
-
(ACL 2022) Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View [Video] [PPT]
-
(ICLR 2021) CoCon: A Self-Supervised Approach for Controlled Text Generation [Video] [PPT]
-
(NAACL 2021) FUDGE: Controlled Text Generation With Future Discriminators [Video] [PPT]
-
(NeurIPS 2021) Controlled Text Generation as Continuous Optimization with Multiple Constraints [Video] [PPT]
-
(ACL 2022) A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation [Video] [PPT]
-
(ACL 2022) Mix and Match: Learning-free Controllable Text Generation using Energy Language Models [Video] [PPT]
-
(ACL 2022) Controllable Natural Language Generation with Contrastive Prefixes [Video] [PPT]
-
(Arxiv) Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation [Video] [PPT]
-
(AAAI 2022) Search and Learn: Improving Semantic Coverage for Data-to-Text Generation [Video] [PPT]
-
(NAACL 2022) Learning to Transfer Prompts for Text Generation [Video] [PPT]
-
(Arxiv) Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation [Video] [PPT]
-
(NeurIPS 2022) Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning [Video] [PPT]
-
(NeurIPS 2022) Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs [Video] [PPT]
-
(NeurIPS 2022) Diffusion-LM Improves Controllable Text Generation [Video] [PPT]
-
(ACL 2020) FLAT: Chinese NER Using Flat-LAttice Transformer [Video] [PPT]
-
(ACL 2021) De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention [Video] [PPT]
-
(CIKM 2020) Mining Infrequent High-Quality Phrases from Domain-Specific Corpora [Video] [PPT]
-
(KDD 2021) UCPhrase: Unsupervised Context-aware Quality Phrase Tagging [Video] [PPT]
-
(NAACL 2021) A Frustratingly Easy Approach for Entity and Relation Extraction [Video] [PPT]
-
(ACL 2022) Packed Levitated Marker for Entity and Relation Extraction [Video] [PPT]
-
(ACL 2020) A Novel Cascade Binary Tagging Framework for Relational Triple Extraction [Video] [PPT]
-
(COLING 2020) TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking [Video] [PPT]
-
(CVPR 2021) Transformation Driven Visual Reasoning [Video] [PPT]
-
(EMNLP 2020) Beyond Language: Learning Commonsense from Images for Reasoning [Video] [PPT]
-
(NeurIPS 2021) Uncertainty calibration for ensemble-based debiasing methods [Video] [PPT]
-
(EMNLP 2021) Adaptive Information Seeking for Open-Domain Question Answering [Video] [PPT]
-
(AAAI 2021) Sketch and Customize: A Counterfactual Story Generator [Video] [PPT]
-
(EMNLP 2021) Transductive Learning for Unsupervised Text Style Transfer [Video] [PPT]
-
(TASLP) Distribution Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains [Video] [PPT]
-
(WSDM 2021) Adversarial Immunization for Certifiable Robustness on Graphs [Video] [PPT]
-
(Nature) Highly accurate protein structure prediction with AlphaFold [Video] [PPT Part 1] [PPT Part2]
-
(DeepMind) Improving language models by retrieving from trillions of tokens [Video] [PPT]
-
(ICLR 2022) Towards a Unified View of Parameter-Efficient Transfer Learning. [Video] [PPT]
-
(ACL 2021) Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases [Video] [PPT]
-
(ACL 2022) Debiased Contrastive Learning of Unsupervised Sentence Representations [Video] [PPT]
-
(ACL 2022) Virtual Augmentation Supported Contrastive Learning of Sentence Representations [Video] [PPT]
-
(EMNLP 2021) SimCSE: Simple Contrastive Learning of Sentence Embeddings [Video] [PPT]
-
(EMNLP 2021) Do Transformer Modifications Transfer Across Implementations and Applications? [Video Part 1] [Video Part 2] [PPT Part 1] [PPT Part 2]
-
(ACL 2022) A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Models [Video] [PPT]
-
(NeurIPS 2021) R-Drop: Regularized Dropout for Neural Networks [Video] [PPT]
-
(ICLR 2022) Language modeling via stochastic processes [Video] [PPT]
-
(NeurIPS 2021) Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [Video] [PPT]
-
(Arxiv) Understanding Diffusion Models: A Unified Perspective [Video Part1] [Video Part2] [Video Part3] [Video Part4] [PPT Part1] [PPT Part2] [PPT Part3] [PPT Part4]
更多内容，欢迎关注我们的微信公众号和B站账号。
同时也欢迎分享自己或他人的顶会文章。投稿请填写揣摩研习社Paper Reading收集表。