- 分享的同学务必提前告知大家分享的论文，并在分享前update paper信息及slides到 52paper.github.io；新人权限开通请联系victoriabi。
- 参与者希望都能够提前把分享的paper进行相关背景的了解，积极提出问题及参与讨论。
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | Recent Advances on controllable text generation | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Yiyang Li | A Brief Introduction to Multi-party Dialogues | [slide] | - |
| - | AAAI 2019 A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues | - | - |
| - | IJCAI 2021 A Structure Self-aware Model for Discourse Parsing on Multi-party Dialogues | - | - |
| - | IJCAI 2019 GSN: A Graph-Structured Network for Multi-Party Dialogues | - | - |
| - | ACL 2022 HeterMPC A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Qian Cao | Recent Advances of Multimodality on Text Generation | [slide] | - |
| - | arXiv 2022 Prefix Language Models are Unified Modal Learners | - | - |
| - | arXiv 2022 Flamingo: a Visual Language Model for Few-Shot Learning | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Leyang Cui | Constituency Parsing | [slide] | - |
| - | ACL 2022 Investigating Non-local Features for Neural Constituency Parsing | - | - |
| - | ACL 2022 Learned Incremental Representations for Parsing | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Haofei Yu | Towards Better Transformer for Long-range Sequence Modeling | [slide] | - |
| - | arXiv 2022 Efficient Transformers: A Survey | - | - |
| - | TACL 2021 Adaptive Semiparametric Language Models | - | - |
| - | ICML 2021 Not All Memories are Created Equal: Learning to Forget by Expiring | - | - |
| - | ICLR 2021 Long Range Arena : A Benchmark for Efficient Transformers | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Xinting Huang | Towards Better Retrievers for Knowledge-intensive Tasks | [slide] | - |
| - | EMNLP 2021 Simple Entity-Centric Questions Challenge Dense Retrievers | - | - |
| - | NeuIPS 2021 BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models | - | - |
| - | TACL 2021 PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them | - | - |
| - | ACL 2020 On the Importance of Diversity in Question Generation for QA | - | - |
| - | ACL Findings 2021 Latent Reasoning for Low-Resource Question Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| qintongli | Explainable Natural Language Processing | [slide] | - |
| - | arXiv 2021 Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing | - | - |
| - | arXiv 2021 Reframing Human-AI Collaboration for Generating Free-Text Explanations | - | - |
| - | ACL Findings 2022 [Event Transition Planning for Open-ended Text Generation] | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Julianjxli | Does the language model understand numbers? | [slide] | - |
| - | EMNLP Findings 2020 Do Language Embeddings Capture Scales? | - | - |
| - | EMNLP 2021 Numeracy enhances the Literacy of Language Models | - | - |
| - | EMNLP Findings 2021 Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model | - | - |
| - | NAACL-HLT 2021 Predicting Numerals in Natural Language Text Using a Language Model Considering the Quantitative Aspects of Numerals | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Tian Lan | Retrieval Augumented Generation | [slide] | - |
| - | arXiv 2020 REALM: Retrieval-Augmented Language Model Pre-Training | - | - |
| - | NIPS 2020 Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | - | - |
| - | ACL 2021 Neural Machine Translation with Monolingual Translation Memory | - | - |
| - | ICLR 2020 Generalization Through Memorization: Nearest Neighbor Language Models | - | - |
| - | arXiv 2021 WebGPT: Browser-assisted question-answering with human feedback | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Chen Xu | Conversational Neuro-Symbolic Commonsense Reasoning | [slide] | - |
| - | AAAI 2021 Conversational Neuro-Symbolic Commonsense Reasoning | - | - |
| - | Arxiv 2021 Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| HAORAN YANG | Adapter Parameter Generation | [slide] | - |
| - | ACL 2021 Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks | - | - |
| - | Arxiv 2021 Lifelong Learning of Few-shot Learners across NLP Tasks | - | - |
| - | ACL 2021 Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Context Information in Language Model | [slide] | - |
| - | ACL 2018 Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context | - | - |
| - | ACL 2020 Do Transformers Need Deep Long-Range Memory | - | - |
| - | ACL 2021 What Context Features Can Transformer Language Models Use | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Qintong Li | Prompting Methods in NLP | [slide] | - |
| - | arXiv 2021 Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing | - | - |
| - | EMNLP 2020 AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts | - | - |
| - | ACL 2021 Prefix-Tuning: Optimizing Continuous Prompts for Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Junjie Wu | Textual Adversarial Attack | [slide] | - |
| - | EMNLP 2020 BERT-ATTACK: Adversarial Attack Against BERT Using BERT | - | - |
| - | Arxiv 2021 Gradient-based Adversarial Attacks against Text Transformers | - | - |
| - | AAAI 2020 Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| LingyunFeng | Sequence Tagging Approaches for Local Sequence Transduction | [slide] | - |
| - | EMNLP 2019 Encode, Tag, Realize: High-Precision Text Editing | - | - |
| - | BEA workshop GECToR – Grammatical Error Correction: Tag, Not Rewrite | - | - |
| - | EMNLP 2020 Seq2Edits: Sequence Transduction Using Span-level Edit Operations | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| johntianlan | Pretrained LM for Dialog Response Selection | [slide] | - |
| - | INTERSPEECH 2020 An Effective Domain Adaptive Post-Training Method for BERT in Response Selection | - | - |
| - | CIKM 2020 Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots | - | - |
| - | AAAI 2021 Do Response Selection Models Really Know What’s Next? Utterance Manipulation Strategies for Multi-turn Response Selection | - | - |
| - | AAAI 2021 Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues | - | - |
| - | ACL 2021 Dialogue Response Selection with Hierarchical Curriculum Learning | - | - |
| - | NAACL 2021 Fine-grained Post-training for Improving Retrieval-based Dialogue Systems | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| HaoranYang | Pretrained LM and Continual Learning | [slide] | - |
| - | TACL 2021 Self-supervised Regularization for Text Classification | - | - |
| - | NAACL 2021 Continual Learning for Text Classification with Information Disentanglement Based Regularization | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| weiwang | MLM and Dialogue | [slide] | - |
| - | Arxiv 2021 Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little | - | - |
| - | Arxiv 2021 Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| xuchen | Persona Dialogue Generation & Knowledge-enhanced Generation | [slide] | - |
| - | ACL2020 You Impress Me: Dialogue Generation via Mutual Persona Perception | - | - |
| - | EMNLP2020 Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | Text Evaluation | [slide] | - |
| - | EMNLP2020 A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing | - | - |
| - | TACL2020 Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Sentence Embedding | [slide] | - |
| - | EMNLP2019 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks | - | - |
| - | Arxiv2020 DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations | - | - |
| - | EMNLP2020 An Unsupervised Sentence Embedding Method by Mutual Information Maximization | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhiyongwu | [slide] | - | |
| - | ACL2020 Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT | - | - |
| - | EMNLP2020 Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rainyucao | Dialogue Data Augmentation | [slide] | - |
| - | EMNLP2020 Dialogue Distillation: Open-domain Dialogue Augmentation Using Unpaired Data | - | - |
| - | EMNLP2020 Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness | - | - |
| - | EMNLP2020 Sequence-Level Mixed Sample Data Augmentation | - | - |
| - | EMNLP2020 SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Best paper of EMNLP 2020 | [slide] | - |
| - | EMNLP2020 Digital Voicing of Silent Speech | - | - |
| - | EMNLP2020 Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems | - | - |
| - | EMNLP2020 GLUCOSE: GeneraLized and COntextualized Story Explanations | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jimblin | Large-scale Retrieval & Language Model | [slide] | - |
| - | WWW2020 Context-Aware Document Term Weighting for Ad-Hoc Search | - | - |
| - | ICLR2020 Pre-training Tasks for Embedding-based Large-scale Retrieval | - | - |
| - | SIGIR2020 ColBERT: Efficient and Eiffective Passage Search via Contextualized Late Interaction over BERT | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickywchen | Evaluation @ EMNLP 2020 (Part 2) | [slide] | - |
| - | EMNLP2020 Evaluating the Factual Consistency of Abstractive Text Summarization | - | - |
| - | EMNLP2020 GRADE- Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems | - | - |
| - | EMNLP2020 UNION-An Unreferenced Metric for Evaluating Open-ended Story Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | Evaluation @ EMNLP 2020 (Part 1) | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zelongyang | Evaluation Metrics For Explainable AI (XAI) | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| haoyusong | Pre-Trained Checkpoints for Warm-Starting of Generation Models | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| thudongwang | Adversarial Training for Pre-trained Models | [slide] | - |
| - | ICLR2020 FreeLB: Enhanced Adversarial Training for Natural Language Understanding | - | - |
| - | ACL2020 SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization | - | - |
| - | arXiv2020 TextAT: Adversarial Training with Token-Aware Perturbation for Natural Language Understanding | - | - |
| - | arXiv2020 Revisiting Pre-Trained Models for Chinese Natural Language Processing | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | A (very) Brief Introduction to Conversational QA | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rainyucao | Graph Pooling | [slide] | - |
| - | NIPS2018 (DiffPool) Hierarchical Graph Representation Learning with Differentiable Pooling | - | - |
| - | ICML2020 (MinCutPool) Spectral Clustering with Graph Neural Networks for Graph Pooling | - | - |
| - | ICML2019 (TopK Pool) Graph U-Nets | - | - |
| - | ICML2019 (SAGPool) Self-Attention Graph Pooling | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Sentence Infilling | [slide] | - |
| - | arxiv2019 Text Infilling | - | - |
| - | IJCAI2019 T-CVAE: Transformer-Based Conditioned Variational Autoencoder for Story Completion | - | - |
| - | ACL2020 INSET: Sentence Infilling with Inter-Sentential Generative Pre-Training | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| robertang | Sentence-level Coherence Modeling | [slide] | - |
| - | ACL2020 Toward Better Storylines with Sentence-Level Language Models | - | - |
| - | ACL2020 Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models | - | - |
| - | ACL2020 Enabling Language Models to Fill in the Blanks | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jamgao | Pretrained Models for Text Generation | [slide] | - |
| - | ACL2020 Distilling Knowledge Learned in BERT for Text Generation | - | - |
| - | ACL2020 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| qintongli | Conversational Reasoning | [slide] | - |
| - | ACL2019 OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs | - | - |
| - | ACL2020 KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation | - | - |
| - | ACL2019 COMET: Commonsense Transformers for Automatic Knowledge Graph Construction | - | - |
| - | ACL2020 MuTual: A Dataset for Multi-Turn Dialogue Reasoning | - | - |
| - | WWW2020 ASER: A Large-scale Eventuality Knowledge Graph | - | - |
| - | IJCAI2020 Guided Generation of Cause and Effect | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| Guanlin Li | Text Generation: related topics | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| charleshao | ACL2020 Excellent Papers | [slide] | - |
| - | ACL2020 Beyond Accuracy: Behavioral Testing of NLP models with CheckList | - | - |
| - | ACL2020 Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks | - | - |
| - | ACL2020 Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rainyucao | Neural Architecture Search | [slide] | - |
| - | JMLR2019 Neural Architecture Search: A Survey | - | - |
| - | ICLR2019 DARTS: Differentiable Architecture Search | - | - |
| - | ICML2019 The Evolved Transformer | - | - |
| - | ACL2019 Continual and Multi-Task Architecture Search | - | - |
| - | EMNLP2019 Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition | - | - |
| - | ACL2020 Learning Architectures from an Extended Search Space for Language Modeling | - | - |
| - | ACL2020 Improving Transformer Models by Reordering their Sublayers | - | - |
| - | ICML2018 Efficient Neural Architecture Search via Parameter Sharing | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zeyuqin | The short introduction to Imbalanced Classification | [slide] | - |
| - | Class-Balanced Loss Based on Effective Number of Samples | - | - |
| - | Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss | - | - |
| - | Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization | - | - |
| - | Decoupling representation and classifier for long-tailed recognition | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | NLP with lage-scale Memory | [slide] | - |
| - | REALM: Retrieval-Augmented Language Model Pre-Training | - | - |
| - | Dense Passage Retrieval for Open-Domain Question Answering | - | - |
| - | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | - | - |
| - | Further reading | - | - |
| - | ACL2019 Latent Retrieval for Weakly Supervised Open Domain Question Answering | - | - |
| - | ACL2019 Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index | - | - |
| - | EMNLP2018 Phrase-Indexed Question Answering- A New Challenge for Scalable Document Comprehension | - | - |
| - | ICLR2020 generalization_through_memorization_nearest_neighbor_language_models | - | - |
| - | NIPS2019 Large Memory Layers with Product Keys | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickywchen | Recent Evaluation Metrics for Text Generation | [slide] | - |
| - | EMNLP2019 MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance | - | - |
| - | ACL2019 A Simple Theoretical Model of Importance for Summarization | - | - |
| - | AAAI2018 RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems | - | - |
| - | NAACL2019 Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| huayangli | The Story about Probing | [slide] | - |
| - | Arxiv2020 Information-Theoretic Probing with Minimum Description Length | - | - |
| - | ACL2020 Information-Theoretic Probing for Linguistic Structure | - | - |
| - | EMNLP2019 Designing and Interpreting Probes with Control Tasks | - | - |
| - | NAACL2019 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | - | - |
| - | NAACL2018 Deep contextualized word representations | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| kaiwang | - | [slide] | - |
| - | ICLR2020 ELECTRA: PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS | - | - |
| - | ACL2019 Bridging the Gap between Training and Inference for Neural Machine Translation | - | - |
| - | ACL2020 Multi-Domain Dialogue Acts and Response Co-Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| haoyusong | Transfer Learning in Personalized Dialogue Generation | [slide] | - |
| - | WWW Journal2019 Neural Personalized Response Generation as Domain Adaptation | - | - |
| - | AAAI2019 short TransferTransfo-A Transfer Learning Approach for Neural Network Based Conversational Agents | - | - |
| - | ACL2019 short Large-scale transfer learning for natural language generation | - | - |
| - | AAAI2020 A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickywchen | Dialogue Summarization | [slide] | - |
| - | ACL2019 (short) Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization | - | - |
| - | KDD2019 Automatic Dialogue Summary Generation for Customer Service | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Some Research Progress on Story Generation | [slide] | - |
| - | CoNLL2019 Do Massively Pretrained Language Models Make Better Storytellers? | - | - |
| - | EMNLP2019 Counterfactual Story Reasoning and Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| hgong | - | [slide] | - |
| - | AAAI2019 Data-to-Text Generation with Content Selection and Planning | - | - |
| - | ACL2019 Data-to-text Generation with Entity Modeling | - | - |
| - | ACL2019 Learning to Select, Track, and Generate for Data-to-Text | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jimblin | - | [slide] | - |
| - | ACL2018 Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network | - | - |
| - | ACL2019 One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues | - | - |
| - | ACL2019 Constructing Interpretive Spatio-Temporal Features for Multi-Turn Response Selection | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| qintongli | - | [slide] | - |
| - | AAAI2018 Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory | - | - |
| - | ACL2018 MOJITALK: Generating Emotional Responses at Scale | - | - |
| - | AAAI2019 An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jiangtongli | ACL Report | [slide] | - |
| - | ACL2019 Bridging the Gap between Training and Inference for Neural Machine Translation | - | - |
| - | ACL2019 OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs | - | - |
| - | ACL2019 Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study | - | - |
| - | ACL2019 Generating Fluent Adversarial Examples for Natural Languages | - | - |
| - | ACL2019 Dynamically Fused Graph Network for Multi-hop Reasoning | - | - |
| - | ACL2019 Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | - | [slide] | - |
| - | ACL2019 Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned | - | - |
| - | ACL2019 Interpretable Neural Predictions with Differentiable Binary Variables | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jiangtongli | Some research progress on sequence generation | [slide] | - |
| - | arXiv2015 How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary? | - | - |
| - | ICML2019 CoT: Cooperative Training for Generative Modeling of Discrete Data | - | - |
| - | ICLR2019 Improving Sequence-to-Sequence Learning via Optimal Transport | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zltian | Triples-to-text generation & its pre-training | [slide] | - |
| - | INLG2018 Deep Graph Convolutional Encoders for Structured Data to Text Generation | - | - |
| - | NAACL2019 Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation | - | - |
| - | NIPS(Workshop)2016 Variational Graph Auto-Encoders | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| rickwwang | Some Research Progress on Story Generation | [slide] | - |
| - | EMNLP2018 A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation | - | - |
| - | AAAI2019 Plan-And-Write: Towards Better Automatic Storytelling | - | - |
| - | ACL2019 Strategies for Structuring Story Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | Rethinking the generation orders of sequence | [slide] | - |
| ICML2019 Insertion Transformer: Flexible Sequence Generation via Insertion Operations | - | - | |
| - | ICML2019 Non-Monotonic Sequential Text Generation | - | - |
| - | arXiv2019 Insertion-based Decoding with automatically Inferred Generation Order | - | - |
| - | EMNLP2018 The Importance of Generation Order in Language Modeling | - | - |
| - | arXiv2019 XLNet: Generalized Autoregressive Pretraining for Language Understanding | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jiachendu | ICLR2019 LEARNING TO REPRESENT EDITS | [slide] | - |
| - | Text Infilling | - | - |
| - | TIGS: An Inference Algorithm for Text Infilling with Gradient Search | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| lixin | The Curious Case of Neural Text Degeneration | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| evanyfgao(高一帆) | Reasoning in Multi-hop Reading Comprehension | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| royrong(荣钰) | Representation Learning on Graphs | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| jcykcai | AAAI2017 Mechanism-Aware Neural Machine for Dialogue Response Generation | [slide] | - |
| - | ACL2018 Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation | - | - |
| - | EMNLP2018 Learning Neural Templates for Text Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| yxsu | TACL2018 Polite Dialogue Generation Without Parallel Data | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | NIPS2018 Content preserving text generation with attribute controls | [slide] | - |
| hongyining | EMNLP2017 Challenges in Data-to-Document Generation | [slide] | - |
| - | Data-to-Text Generation with Content Selection and Planning | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhuqile | ICLR2019 Recent Advances in Autoencoder-Based Representation Learning | [slide] | - |
| jiangtongli | ICLR2019 Pay Less Attention with Lightweight and Dynamic Convolutions | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhuqile | ICLR2019 Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow | [slide] | - |
| - | ICLR2017 Deep Variational Information Bottleneck | - | - |
| jiangtongli | COLING2018 Modeling Multi-turn Conversation with Deep Utterance Aggregation | [slide | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| yxsu | SIGHAN2018 Group Linguistic Bias Aware Neural Response Generation | [slide] | - |
| Shangmingyue | Arxiv2018 Dialogue Natural Language Inference | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| lixin | EMNLP2018 Semi-Supervised Learning for Neural Keyphrase Generation | [slide] | - |
| gaojun | ACL2018 Hierarchical Neural Story Generation | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaoyifan | AAAI2019 A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhufengpan | COLING2016 Non-sentential Question Resolution using Sequence to Sequence Learning | [slide] | - |
| - | SIGIR2017 Incomplete Follow-up question Resolution using Retrieval based Sequence to Sequence Learning | - | [dataset] |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhaoyang | ICLR2018(under review)I Know the Feeling: Learning to Converse with Empathy | [slide] | - |
| jcykcai | NIPS2018 Deep Generative Models with Learnable Knowledge Constraints | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaoyifan | ACL2018 Harvesting Paragraph-Level Question-Answer Pairs from Wikipedia | [slide] | - |
| shangmingyue | NIPS2017 Adversarial Ranking for Language Generation | [slide] | - |
| - | AAAI2018 Long Text Generation via Adversarial Training with Leaked Information | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | NAACL2017 Deep contextualized word representations | [slide] | - |
| - | Arxiv2018 Improving Language Understanding by Generative Pre-Training | - | - |
| - | Arxiv2018 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| lixin | ACL2017 Neural Belief Tracker: Data-Driven Dialogue State Tracking | [slide] | - |
| - | ACL2018 Global-Locally Self-Attentive Encoder for Dialogue State Tracking | - | - |
| - | ICASSP2018 Adversarial Actor-Critic Model For Task-Completion Dialogue Policy Learning | - | - |
| - | ACL2018 Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| cd | NIPS2018 Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization | [slide] | - |
| EMNLP2017 Sequential Matching Network-A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots | - | ||
| zhaoyang | ACL2018 Learning to Control the Specificity in Neural Response Generation | [slide] | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | NIPS2017 Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space | [slide] | - |
| cd | arXiv2018 Response Generation by Context-aware Prototype Editing | [slide] | - |
| - | arXiv2016 Two are better than one: An ensemble of retrieval-and generation-based dialog systems | - | - |
| zhaoyang | AAAI2018 Dictionary-Guided Editing Networks for Paraphrase Generation | [slide] | - |
| ziyang | ACL2018 Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information | [slide] | - |
| biwei | - | - | - |
| yahui | ACL2018 Token-level and sequence-level loss smoothing for RNN language models | [slide] | - |
| - | arXiv2018 Sounding Board: A User-Centric and Content-Driven Social Chatbot | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| zhaoyang | ACL2018 Report | slide | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | ACL2017 Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning | [slide] | - |
| cd | ACL18 AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples | [slide] | - |
| - | ACL18 Working Memory Networks-Augmenting Memory Networks with a Relational Reasoning Module | - | - |
| ziyang | IJCAI2018 SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks | [slide] | - |
| biwei | - | - | - |
| yahui | AAAI2015 Self-Paced Curriculum Learning | [slide] | - |
| - | ICML2018 MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| gaojun | AAAI2018 Flexible End-to-End Dialogue System for Knowledge Grounded Conversation | [slide] | - |
| cd | Nature2017 Mastering the game of Go Without human knowledge | [slide] | - |
| ziyang | CVPR2018 Video Captioning via Hierarchical Reinforcement Learning | [slide] | - |
| biwei | ICML2017 FeUdal Networks for Hierarchical Reinforcement Learning | [slide] | - |
| yahui | IJCAI2018 Learning to Converse with Noisy Data: Generation with Calibration | [slide] | - |
| - | arXiv2016 Data Distillation for Controlling Specificity in Dialogue Generation | - | - |
| Speakers | Papers | Slides | Others |
|---|---|---|---|
| xiaojiang | review questions about GAN again and summarize GAN's possible use in conversation resposne geneartion. | - | - |
| gaojun | IJCAI2016 Neural Generative Question Answering | [slide] | - |
| - | AAAI2018 A Knowledge-Grounded Neural Conversation Model | - | - |
| cd | ACL2018 Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting | [slide] | - |
| - | ACL2018 Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach | - | - |
| yahui | NAACL2018 Discourse-Aware Neural Rewards for Coherent Text Generation | [slide] | Report of GAN |
| biwei | ICML2017 Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control | [slide] | - |
- xiaojiang's questions, hope we could have agreements on these three points, and output some reports:
- Why Seq2seq is better than the previous language model methods in generating language sequence. Why GAN is better than standard Seq2seq?
- GAN has been successfully appllied to many new image tasks, such as image generation. What are the best tasks of GAN for text?
- Why GAN has no break-through on text yet? All possible reasons.
| Lecturers | Papers | Slides | Others |
|---|---|---|---|
| cd | Implement Adversarial Training for Text Generation (motivations and technologies) | [slide] | - |
| gaojun | EMNLP2017 Neural Response Generation via GAN with an Approximate Embedding Layer∗ | [slide] | - |
| - | IJCAI2018 Commonsense Knowledge Aware Conversation Generation with Graph Attention | - | - |
| yahui | EMNLP2017 Adversarial Learning for Neural Dialogue Generation | [slide] | - |
| - | ICLR2018 MaskGAN: Better Text Generation via Filling in the __ | - | - |
| biwei | ICML2017 Adversarial Feature Matching for Text Generation | [slide] | - |