NLP-2021-调研

• 会议：conference${}^{GoogleScholarRank-CCFRank}$(link): time
• 榜单：(部分数据集)${}^{year(link)lang(paper)}$
• 任务：细化+多模态/多任务

会议

• EACL${}^7$: 2020/10/7
• ACL${}^{1-A}$: 2021/1/25
• ICML${}^{3-A}$: 2021/1/28
• SIGIR${}^A$: 2021/1/28
• IJCAI${}^{10-A}$: 2021/1/13
• EMNLP${}^{2-B}$: 2021/5/10
• NeurIPS${}^{2-A}$: 2021/5/19

榜单

任务/方法	数据集
信息抽取	HOVER${}^{20}$${}^{en}$ MAVEN${}^{20}$${}^{en}$ FewRel 1.0${}^{18}$${}^{en}$ SemEval2010 Task 8${}^{10}$${}^{en}$ KnowledgeNet${}^{19}$${}^{en}$ Evidence Inference${}^{19}$${}^{en}$ DialogRE${}^{20}$${}^{ch,en}$ BC2GM${}^{08}$${}^{en}$ BC5-Chem${}^{16}$${}^{en}$ BC5-Disease${}^{15}$${}^{en}$ JNLPBA${}^{04}$${}^{en}$ NCBI Disease Corpus${}^{14}$${}^{en}$ ChemProt${}^{17}$${}^{en}$ DDI${}^{13}$${}^{en}$ GAD${}^{04}$${}^{en}$ ADE${}^{12}$${}^{en}$ The New York Times Annotated Corpus${}^{08}$${}^{en}$ DNA Methylation Corpus${}^{10}$${}^{en}$ Exhaustive PTM Corpus${}^{11}$${}^{en}$ mTOR Pathway Corpus${}^{11}$${}^{en}$ PTM Event Corpus${}^{10}$${}^{en}$ T4SS Event Corpus${}^{10}$${}^{en}$ AMR${}^{20}$${}^{en}$ feSciREX${}^{20}$${}^{en}$ Personal Events in Dialogue Corpus${}^{20}$${}^{en}$ Quda${}^{20}$${}^{en}$ FOBIE${}^{20}$${}^{en}$ Deft${}^{19}$${}^{en}$ DocRed${}^{19}$${}^{en}$ TACRED${}^{17}$${}^{en}$ QA-ZRE${}^{17}$${}^{en}$ Relation Extraction Corpus${}^{13}$${}^{en}$ OPIEC${}^{19}$${}^{en}$ Automatic Keyphrase Extraction${}^{1999-2008}$${}^{en}$ NYSK Dataset${}^{13}$${}^{en}$ T-REx${}^{18}$${}^{en}$
阅读理解	IIRC${}^{20}$${}^{en}$ SLURP${}^{20}$${}^{en}$ ChID(CLUE Benchmark)${}^{20}$${}^{ch}$ LogiQA${}^{20}$${}^{en}$ AmbigNQ${}^{20}$${}^{en}$ DREAM${}^{19}$${}^{en}$ OneStopQA${}^{20}$${}^{en}$ emrQA${}^{18}$${}^{en}$ SelQA${}^{16}$${}^{en}$ CMRC${}^{20}$${}^{ch}$ ReClor${}^{20}$${}^{en}$ MathQA${}^{19}$${}^{en}$ CMRC 2018${}^{18}$${}^{ch}$ Delta Reading Comprehension Dataset${}^{19}$${}^{ch}$ ELI5${}^{19}$${}^{en}$ ComQA${}^{19}$${}^{en}$ MLQA${}^{19}$${}^{multi}$ QASC${}^{20}$${}^{en}$ Quoref${}^{19}$${}^{en}$ InsuranceQA${}^{15}$${}^{en}$ CoQA${}^{19}$${}^{en}$ DROP${}^{19}$${}^{en}$ ARC${}^{18}$${}^{en}$ AI2 Science Questions Mercury${}^{17}$${}^{en}$ AI2 Science Questions v2.1${}^{17}$${}^{en}$ AQuA${}^{17}$${}^{en}$ CBT${}^{16}$${}^{en}$ CliCR${}^{18}$${}^{en}$ CNN / Daily Mail Dataset${}^{15}$${}^{en}$ CODAH${}^{19}$${}^{en}$ CommonsenseQA${}^{18}$${}^{en}$ Cosmos QA${}^{19}$${}^{en}$ Dataset for the Machine Comprehension of Text${}^{13}$${}^{en}$ Explanations for Science Questions${}^{16}$${}^{en}$ HotpotQA${}^{18}$${}^{en}$ HITL${}^{16}$${}^{en}$ Jeapardy Questions Answers${}^{19}$${}^{en}$ MS MARCO${}^{16}$${}^{en}$ RecipeQA${}^{18}$${}^{en}$ NarrativeQA${}^{17}$${}^{en}$ NQ${}^{19}$${}^{en}$ NewsQA${}^{17}$${}^{en}$ OpenBookQA${}^{18}$${}^{en}$ ProPara Dataset${}^{18}$${}^{en}$ QuaRel Dataset${}^{18}$${}^{en}$ QuaRTz Dataset${}^{19}$${}^{en}$ Quasar-S & T${}^{17}$${}^{en}$ QuAC${}^{18}$${}^{en}$ RACE${}^{17}$${}^{en}$ MultiRC${}^{18}$${}^{en}$ Record${}^{18}$${}^{en}$ Qangaroo${}^{18}$${}^{en}$ SciQ Dataset${}^{17}$${}^{en}$ SearchQA${}^{17}$${}^{en}$ ShARC${}^{18}$${}^{en}$ SWAG${}^{18}$${}^{en}$ SQuAD v2.0${}^{18}$${}^{en}$ The Dialog-based Language Learning Dataset${}^{16}$${}^{en}$ The Movie Dialog Dataset${}^{16}$${}^{en}$ The Story Cloze Test
命名实体识别	WikiNER${}^{13}$${}^{multi}$ CoNLL 2003 ++${}^{20}$${}^{en}$ WNUT${}^{16}$${}^{en}$ BC2GM${}^{08}$${}^{en}$ BC5-Chem${}^{16}$${}^{en}$ BC5-Disease${}^{15}$${}^{en}$ JNLPBA${}^{04}$${}^{en}$ NCBI Disease Corpus${}^{14}$${}^{en}$ ScienceExamCER${}^{19}$${}^{en}$ WNUT 2017${}^{17}$${}^{en}$ BSNLP-2019${}^{19}$${}^{multi}$ WikiAnn${}^{17}$${}^{multi}$ LitBank${}^{19}$${}^{en}$
问答	XQuaD-R${}^{20}$${}^{multi}$ SubjQA${}^{20}$${}^{en}$ EXAMS${}^{20}$${}^{multi}$ 2WikiMultihopQA${}^{20}$${}^{en}$ ORConvQA${}^{20}$${}^{en}$ GrailQA${}^{20}$${}^{en}$ OTT-QA${}^{20}$${}^{en}$ LiveQA${}^{20}$${}^{ch}$ C3${}^{20}$${}^{en}$ LogiQA${}^{20}$${}^{en}$ MKQA${}^{20}$${}^{multi}$ QED${}^{20}$${}^{en}$ PubmedQA${}^{19}$${}^{en}$ Worldtree Corpus${}^{20}$${}^{en}$ ManyModalQA${}^{20}$${}^{en}$ Get it #OffMyChest${}^{20}$${}^{en}$ AirDialogue${}^{18}$${}^{en}$ AmbigNQ${}^{20}$${}^{en}$ OpenKP${}^{19}$${}^{en}$ DREAM${}^{19}$${}^{en}$ OneStopQA${}^{20}$${}^{en}$ DoQa${}^{20}$${}^{en}$ DramaQA${}^{20}$${}^{en}$ emrQA${}^{18}$${}^{en}$ FreebaseQA${}^{19}$${}^{en}$ SelQA${}^{16}$${}^{en}$ MATINF${}^{20}$${}^{ch}$ EventQA${}^{19}$${}^{en}$ SQA${}^{16}$${}^{en}$ WikiTablesQuestions${}^{15}$${}^{en}$ CSQA${}^{18}$${}^{en}$ HybridQA${}^{20}$${}^{en}$ CFQ${}^{20}$${}^{en}$ MetaQA${}^{18}$${}^{en}$ WebQuestions${}^{13}$${}^{en}$ MathQA${}^{19}$${}^{en}$ CMRC 2018${}^{18}$${}^{ch}$ Delta Reading Comprehension Dataset${}^{19}$${}^{ch}$ LC-QuAD 2.0${}^{17}$${}^{en}$ ELI5${}^{19}$${}^{en}$ ComQA${}^{19}$${}^{en}$ MLQA${}^{19}$${}^{multi}$ QASC${}^{20}$${}^{en}$ Quoref${}^{19}$${}^{en}$ InsuranceQA${}^{15}$${}^{en}$ Physical IQA${}^{19}$${}^{en}$ QA-SRL Bank${}^{18}$${}^{en}$ QA-ZRE${}^{17}$${}^{en}$ Social IQA${}^{19}$${}^{en}$ CoQA${}^{19}$${}^{en}$ DROP${}^{19}$${}^{en}$ ARC${}^{18}$${}^{en}$ AI2 Science Questions v2.1${}^{17}$${}^{en}$ AQuA${}^{17}$${}^{en}$ BoolQ${}^{19}$${}^{en}$ CBT${}^{16}$${}^{en}$ CliCR${}^{18}$${}^{en}$ CNN / Daily Mail Dataset${}^{15}$${}^{en}$ CODAH${}^{19}$${}^{en}$ CommonsenseQA${}^{18}$${}^{en}$ ComplexWebQuestions${}^{18}$${}^{en}$ Cosmos QA${}^{19}$${}^{en}$ Dataset for the Machine Comprehension of Text${}^{13}$${}^{en}$ Explanations for Science Questions${}^{16}$${}^{en}$ HotpotQA${}^{18}$${}^{en}$ HITL${}^{16}$${}^{en}$ Jeapardy Questions Answers${}^{19}$${}^{en}$ MS MARCO${}^{16}$${}^{en}$ RecipeQA${}^{18}$${}^{en}$ NarrativeQA${}^{17}$${}^{en}$ NQ${}^{19}$${}^{en}$ NewsQA${}^{17}$${}^{en}$ OpenBookQA${}^{18}$${}^{en}$ ProPara Dataset${}^{18}$${}^{en}$ QuaRel Dataset${}^{18}$${}^{en}$ QuaRTz Dataset${}^{19}$${}^{en}$ Quasar-S & T${}^{17}$${}^{en}$ QuAC${}^{18}$${}^{en}$ RACE${}^{17}$${}^{en}$ MultiRC${}^{18}$${}^{en}$ Record${}^{18}$${}^{en}$ Qangaroo${}^{18}$${}^{en}$ SciQ Dataset${}^{17}$${}^{en}$ SearchQA${}^{17}$${}^{en}$ ShARC${}^{18}$${}^{en}$ SWAG${}^{18}$${}^{en}$ SQuAD v2.0${}^{18}$${}^{en}$ The Dialog-based Language Learning Dataset${}^{16}$${}^{en}$ The Movie Dialog Dataset${}^{16}$${}^{en}$ The SimpleQuestions Dataset${}^{15}$${}^{en}$ The Story Cloze Test | ROCStories${}^{17}$${}^{en}$ The WikiMovies Dataset${}^{16}$${}^{en}$ TrecQA${}^{07}$${}^{en}$ TriviaQA${}^{17}$${}^{en}$ Who Did What Dataset${}^{16}$${}^{en}$ WikiQA Corpus${}^{15}$${}^{en}$
对话	MedDialog${}^{20}$${}^{ch}$ TreeDST${}^{20}$${}^{en}$ Taskmaster-3${}^{20}$${}^{en}$ STAR${}^{20}$${}^{en}$ RiSAWOZ${}^{20}$${}^{ch}$ SIMMC${}^{20}$${}^{en}$ DialoGLUE${}^{20}$${}^{en}$ MedDG${}^{20}$${}^{ch}$ C3${}^{20}$${}^{en}$ DailyDialog++${}^{20}$${}^{en}$ SMCalFlow${}^{20}$${}^{en}$ CRD3${}^{20}$${}^{en}$ ClariQ${}^{20}$${}^{en}$ DialogRE${}^{20}$${}^{ch,en}$ CraigsListBargain${}^{18}$${}^{en}$ KVRET${}^{17}$${}^{en}$ MMD${}^{17}$${}^{en}$ DREAM${}^{19}$${}^{en}$ AVSD${}^{19}$${}^{en}$ DoQa${}^{20}$${}^{en}$ IRC Disentanglement${}^{19}$${}^{en}$ Frames${}^{17}$${}^{en}$ Gutenberg Dialogue${}^{20}$${}^{multi}$ OpenDialKG${}^{19}$${}^{en}$ MuTual${}^{20}$${}^{en}$ KdConv${}^{20}$${}^{ch}$ CrossWOZ${}^{20}$${}^{ch}$ Taskmaster-2${}^{20}$${}^{en}$ Background Knowledge Dialogue Dataset${}^{18}$${}^{en}$ NLI${}^{19}$${}^{en}$ EmpatheticDialogues${}^{19}$${}^{en}$ OneCommon${}^{19}$${}^{en}$ Twitter Chat Corpus${}^{17}$${}^{en}$ Soccer Dialogues${}^{19}$${}^{en}$ Soccer Dialogues${}^{19}$${}^{en}$ SwDA${}^{97}$${}^{en}$ babI 6 Tasks Dialogue${}^{17}$${}^{en}$ Coached Conversational Preference Elicitation${}^{19}$${}^{en}$ Cornell Movie–Dialogs Corpus${}^{11}$${}^{en}$ Deal or No Deal? End-to-End Learning for Negotiation Dialogues${}^{17}$${}^{en}$ MetaLWOz${}^{19}$${}^{en}$ MultiWoz${}^{18}$${}^{en}$ MutualFriends${}^{17}$${}^{en}$ NPS Chat Corpus${}^{07}$${}^{en}$ Personalized Dialog${}^{17}$${}^{en}$ DSTC 8${}^{19}$${}^{en}$ Taskmaster-1${}^{19}$${}^{en}$ ConvAI2${}^{18}$${}^{en}$ Topical-Chat${}^{19}$${}^{en}$ Ubuntu Dialogue Corpus${}^{15}$${}^{en}$ UseNet Corpus${}^{11}$${}^{en}$
情感分析	SigmaLaw-ABSA${}^{20}$${}^{en}$ PerSenT${}^{20}$${}^{en}$ XED${}^{20}$${}^{multi}$ FinancialPhraseBank${}^{14}$${}^{en}$ Crema-D${}^{14}$${}^{en}$ Yelp Polarity Reviews${}^{15}$${}^{en}$ GoEmotions${}^{20}$${}^{en}$ Clash of Clans${}^{19}$${}^{en}$ MPQA Opinion Corpus${}^{15}$${}^{en}$ WikiTablesQuestions${}^{15}$${}^{en}$ SemEval-2016 Task 4${}^{16}$${}^{en}$ ArguAna TripAdvisor Corpus${}^{14}$${}^{en}$ Large Movie Review Dataset-Imdb${}^{11}$${}^{en}$ Irony Sarcasm Analysis Corpus${}^{16}$${}^{en}$ Affective Text${}^{07}$${}^{en}$ Classify Emotional Relationships of Fictional Characters${}^{19}$${}^{en}$ DailyDialog${}^{17}$${}^{en}$ Emotion-Stimulus${}^{15}$${}^{en}$ The Emotion in Text${}^{16}$${}^{en}$ Amazon Fine Food Reviews${}^{13}$${}^{en}$ Amazon Reviews${}^{18}$${}^{en}$ Blogger Authorship Corpus${}^{06}$${}^{en}$ MSParS${}^{19}$${}^{en}$ NYSK Dataset${}^{13}$${}^{en}$ Sentiment Labeled Sentences Dataset${}^{15}$${}^{en}$ Sentiment140${}^{09}$${}^{en}$ Skytrax User Reviews Dataset${}^{15}$${}^{en}$ SST${}^{13}$${}^{en}$ WebQuestions Semantic Parses Dataset${}^{16}$${}^{en}$ Yelp Open Dataset${}^{15}$${}^{en}$
知识库	WebChild${}^{14}$${}^{en}$ ENT-DESC${}^{20}$${}^{en}$ KELM${}^{20}$${}^{en}$ Olpbench${}^{20}$${}^{en}$ KnowledgeNet${}^{19}$${}^{en}$ Worldtree Corpus${}^{20}$${}^{en}$ WordNet${}^{06}$${}^{en}$ FB15K-237 Knowledge Base Completion Dataset${}^{15}$${}^{en}$ WN18RR${}^{18}$${}^{en}$ ATOMIC${}^{18}$${}^{en}$ ConceptNet${}^{17}$${}^{multi}$ FreebaseQA${}^{19}$${}^{en}$ EventQA${}^{19}$${}^{en}$ CSQA${}^{18}$${}^{en}$ Linked WikiText-2${}^{19}$${}^{en}$ OpenDialKG${}^{19}$${}^{en}$ HybridQA${}^{20}$${}^{en}$ KdConv${}^{20}$${}^{ch}$ CFQ${}^{20}$${}^{en}$ MetaQA${}^{18}$${}^{en}$ WebQuestions${}^{13}$${}^{en}$ LC-QuAD 2.0${}^{17}$${}^{en}$ KDWD${}^{20}$${}^{en}$ ReVerb45k, Base and Ambiguous${}^{18}$${}^{en}$ Dialogues${}^{19}$${}^{en}$ Soccer Dialogues${}^{19}$${}^{en}$ OPIEC${}^{19}$${}^{en}$ Aristo Tuple KB${}^{17}$${}^{en}$ ComplexWebQuestions${}^{18}$${}^{en}$ The SimpleQuestions Dataset${}^{15}$${}^{en}$ TupleInf Open IE Dataset${}^{17}$${}^{en}$
多模态	KB-Ref${}^{20}$${}^{en}$ SIMMC${}^{20}$${}^{en}$ Visual Genome${}^{16}$${}^{en}$ Visual Commonsense Graphs${}^{20}$${}^{en}$ FigureQA${}^{18}$${}^{en}$ Hateful Memes${}^{20}$${}^{en}$ TVQA${}^{18}$${}^{en}$ MovieQA${}^{16}$${}^{en}$ Crema-D${}^{14}$${}^{en}$ VQA-Introspect${}^{20}$${}^{en}$ SVT${}^{12}$${}^{en}$ AVSD${}^{19}$${}^{en}$ ALFRED${}^{20}$${}^{en}$ VIST${}^{16}$${}^{en}$ VIOLIN${}^{20}$${}^{en}$ MUStARD${}^{19}$${}^{en}$ MELD${}^{18}$${}^{en}$ CLEVR & CoGenT${}^{16}$${}^{en}$ FVQA${}^{17}$${}^{en}$ VisDial${}^{17}$${}^{en}$ Activitynet-QA${}^{19}$${}^{en}$ CMU-MOSEI${}^{18}$${}^{en}$ DVQA${}^{18}$${}^{en}$ GQA${}^{19}$${}^{en}$ Social-IQ Dataset${}^{19}$${}^{en}$ Textbook Question Answering${}^{17}$${}^{en}$ TextVQA${}^{19}$${}^{en}$ Twitter100k${}^{17}$${}^{en}$ VCR${}^{18}$${}^{en}$ VQA${}^{15}$${}^{en}$
文本分类	SBIC${}^{20}$${}^{en}$ TweetEval${}^{20}$${}^{en}$ AFQMC(CLUE Benchmark)${}^{20}$${}^{ch}$ TNEWS(CLUE Benchmark)${}^{20}$${}^{ch}$ IFLYTEK (CLUE Benchmark)${}^{20}$${}^{ch}$ NatCat${}^{20}$${}^{en}$ OLID${}^{19}$${}^{en}$ EPIE${}^{20}$${}^{en}$ SOCC${}^{18}$${}^{en}$ C3${}^{20}$${}^{en}$ LEDGAR${}^{20}$${}^{en}$ HoC${}^{16}$${}^{en}$ TRACT${}^{20}$${}^{en}$ Humicroedit${}^{19}$${}^{en}$ FEVER${}^{18}$${}^{en}$ ColBERT${}^{20}$${}^{en}$ SemEval-2019 Task 6${}^{19}$${}^{en}$ Ohsumed Dataset${}^{97}$${}^{en}$ The EUR-Lex Dataset${}^{10}$${}^{multi}$ PubMed 200k RCT Dataset${}^{17}$${}^{en}$ MATINF${}^{20}$${}^{ch}$ NELA-GT-2019${}^{20}$${}^{en}$ SemEval-2016 Task 4${}^{16}$${}^{en}$ ArguAna TripAdvisor Corpus${}^{14}$${}^{en}$ AG News${}^{15}$${}^{en}$ Large Movie Review Dataset-Imdb${}^{11}$${}^{en}$ aNLI${}^{19}$${}^{en}$ NLVR and NLVR2${}^{19}$${}^{en}$ EmoBank${}^{17}$${}^{en}$ Irony Sarcasm Analysis Corpus${}^{16}$${}^{en}$ Dataset for Intent Classification and Out-of-Scope Prediction${}^{19}$${}^{en}$ SMM4H${}^{18}$${}^{en}$ Amazon Fine Food Reviews${}^{13}$${}^{en}$ Amazon Reviews${}^{18}$${}^{en}$ Blogger Authorship Corpus${}^{06}$${}^{en}$ Buzz in Social Media Dataset${}^{13}$${}^{en}$ Car Evaluation Dataset${}^{97}$${}^{en}$ ClueWeb Corpora${}^{13}$${}^{en}$ Corporate Messaging Corpus${}^{15}$${}^{en}$ DEXTER Dataset${}^{08}$${}^{en}$ Home Depot Product Search Relevance${}^{15}$${}^{en}$ Legal Case Reports${}^{12}$${}^{en}$ Ling-Spam Dataset${}^{00}$${}^{en}$ Reuters-21578 Benchmark Corpus${}^{97}$${}^{en}$ Sentiment Labeled Sentences Dataset${}^{15}$${}^{en}$ Sentiment140${}^{09}$${}^{en}$ Skytrax User Reviews Dataset${}^{15}$${}^{en}$ SMS Spam Collection Dataset${}^{11}$${}^{en}$ Spambase Dataset${}^{99}$${}^{en}$ SST${}^{13}$${}^{en}$ Twitter US Airline Sentiment${}^{16}$${}^{en}$ Web of Science Dataset${}^{17}$${}^{en}$ Yelp Open Dataset${}^{15}$${}^{en}$ YouTube Comedy Slam Preference Dataset${}^{12}$${}^{en}$

任务

任务	细化+多模态/多任务
文本向量化	词向量+句向量+文本向量+阅读理解
序列标注	命名实体识别+机器翻译+文本生成+句法分析
文本分类	情感分析+文本向量化+文本相似度+消歧+少样本识别+推理
信息提取	实体抽取+关系抽取+事件抽取
场景任务	聊天机器人+推荐系统+问答系统+知识图谱

参考

2021年NLP重要国际会议时间
The Big Bad NLP Database
【NLP】一文汇总自然语言处理主要研究方向