ACL2020錄取文章已經放出，連接以下：node
ACL2020論文集合 www.aclweb.org爲了之後更加方便地閱讀論文，也本着一顆開源之心，花一個下午的時間整理了一下相關論文。鑑於本人精力有限，而且也只在NLP領域作過部分任務，所以只整理了如下四種任務的論文：（1）預訓練語言模型及部分應用（18篇）；（2）QA問答系統及機器閱讀理解（13篇）；（3）問題生成（7篇）；（4）天然語言推理（文本蘊含or文本匹配）（4篇）。git
歡迎你們進行補充~~~~~~github
1、預訓練語言模型及部分應用
（1）QuASE: Question-Answer Driven Sentence Encodingweb
（2）TaBERT: Pretraining for Joint Understanding of Textual and Tabular Dataapp
（3）Don’t Stop Pretraining: Adapt Language Models to Domains and Tasksflex
（4）BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensionspa
（5）Toward Better Storylines with Sentence-Level Language Models
（6）tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection
（7）FastBERT: a Self-distilling BERT with Adaptive Inference Time
（8）Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models
（9）DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
（10）Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention
（11）schuBERT: Optimizing Elements of BERT
paper：論文
（12）Span Selection Pre-training for Question Answering
（13）DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
（14）MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
（15）A Generative Model for Joint Natural Language Understanding and Generation
paper：論文
（16）Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
（17）Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order
paper：論文
（18）Few-Shot NLG with Pre-Trained Language Model
2、QA問答系統及機器閱讀理解
（1）DoQA - Accessing Domain-Specific FAQs via Conversational QA
（2）CorefQA: Coreference Resolution as Query-based Span Prediction
（3）RikiNet: Reading Wikipedia Pages for Natural Question Answering
paper：論文
（4）Harvesting and Refining Question-Answer Pairs for Unsupervised QA
（5）Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
（6）Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering
（7）Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
（8）Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension
（9）Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
（10）Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
（11）Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
（12）A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
paper：論文
（13）A Frame-based Sentence Representation for Machine Reading Comprehension
paper：論文
3、問題生成
（1）ClarQ: A large-scale and diverse dataset for Clarification Question Generation
（2）How to Ask Good Questions? Try to Leverage Paraphrases
paper：論文
（3）On the Importance of Diversity in Question Generation for QA
paper：論文
（4）Semantic Graphs for Generating Deep Questions
（5）Unsupervised FAQ Retrieval with Question Generation and BERT
（6）Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation
（7）Low-Resource Generation of Multi-hop Reasoning Questions
paper：論文
4、天然語言推理（文本蘊含or文本匹配）
（1）Uncertain Natural Language Inference
（2）Towards Robustifying NLI Models Against Lexical Dataset Biases
（3）NILE : Natural Language Inference with Faithful Natural Language Explanations
（4）Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport
ACL2020共收錄了779篇論文，整理下來實屬不易，還請你們多多點贊~~~
鑑於本人僅對上述幾個任務有所涉及，所以只整理了這幾個模塊；其餘小夥伴若是有一些建議或願意一塊兒整理，能夠留言，會持續更新~~~~
接下來，有可能會進一步進行解讀，將論文摘要部分添加進來，給更多小夥伴提供方便。
廣告時間，哈哈哈哈。推薦幾篇本人以前寫的一些文章：