20篇「ACL2020」!抢先看自然语言处理2020在研究什么?

2020-05-20 23:06:55 浏览数 (1)

The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020) 将于2020年7月5日至10日美国华盛顿州西雅图举行,不过今年因新冠将在线举办ACL年会是计算语言学和自然语言处理领域最重要的顶级国际会议,CCF A类会议,由计算语言学协会主办,每年举办一次。其接收的论文覆盖了对话交互系统、语义分析、摘要生成、信息抽取、问答系统、文本挖掘、机器翻译、语篇语用学、情感分析和意见挖掘、社会计算等自然语言处理领域众多研究方向。该会议的论文基本代表自然语言处理领域最新研究进展和最高研究水平,受到学术界和产业界的高度关注。

1. BPE-Dropout:简单有效的子词正则化,Simple and Effective Subword Regularization,俄罗斯Yandex

https://arxiv.org/abs/1910.13267

2. 预训练语言模型中的跨语言结构,Emerging Cross-lingual Structure in Pretrained Language Models,Facebook

https://arxiv.org/abs/1911.01464

3. 大规模无监督跨语言表示学习,Unsupervised Cross-lingual Representation Learning at Scale,Facebook AI

https://arxiv.org/abs/1911.02116

4. 学习鲁棒度量的文本生成,BLEURT: Learning Robust Metrics for Text Generation,Google

https://arxiv.org/pdf/2004.04696.pdf

5. 基于领域自适应的减少神经机器翻译中的性别偏见,Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem,剑桥大学

https://arxiv.org/pdf/2004.04498.pdf

6. 在语言模型中注入数值推理技巧,Injecting Numerical Reasoning Skills into Language Models,Allen AI

https://arxiv.org/pdf/2004.04487.pdf

7. 多轮对话数据集,MuTual: A Dataset for Multi-Turn Dialogue Reasoning,浙大,微软

https://arxiv.org/pdf/2004.04494.pdf

8. TAPAS:通过预训练进行的弱监督表解析,TAPAS: Weakly Supervised Table Parsing via Pre-training,谷歌

https://arxiv.org/pdf/2004.02349.pdf

9. 提高神经语言模型句法能力,An analysis of the utility of explicit negative examples to improve the syntactic abilities of neural language models,谷歌

https://arxiv.org/pdf/2004.02451.pdf

10. 多级学习排序的层次实体标注,Hierarchical Entity Typing via Multi-level Learning to Rank,霍普金斯大学

https://arxiv.org/pdf/2004.02286.pdf

11. 数据操作:通过学习增加和调整权重,实现有效的实例学习,生成神经对话,Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight,中科院计算所

https://arxiv.org/pdf/2004.02594.pdf

12. 法律判决,Distinguish Confusing Law Articles for Legal Judgment Prediction,西安交大

https://arxiv.org/pdf/2004.02557.pdf

13. MobileBERT:用于资源受限设备的任务无关“瘦版”BERT,MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices,谷歌

https://arxiv.org/pdf/2004.02984.pdf

14. 信息论探索语言结构,Information-Theoretic Probing for Linguistic Structure,剑桥

https://arxiv.org/pdf/2004.03061.pdf

15. 多方对话学习层次结构,Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering,EMORY

https://arxiv.org/pdf/2004.03561.pdf

16. 对话学习器,Conversation Learner – A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems,微软

https://arxiv.org/pdf/2004.04228.pdf

17. 反对网络仇恨言论的反叙述:数据和策略,Generating Counter Narratives against Online Hate Speech: Data and Strategies

https://arxiv.org/pdf/2004.04216.pdf

18. 多语言序列标记的结构层次知识提取,Structure-Level Knowledge Distillation For Multilingual Sequence Labeling,上科大,阿里巴巴达摩院

https://arxiv.org/pdf/2004.03846.pdf

19. 基于角色感知奖励分解的多代理面向任务的对话策略学习,Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition,清华大学

https://arxiv.org/pdf/2004.03809.pdf

20. FastBERT:一种具有自适应推理时间的自适应BERT?,FastBERT: a Self-distilling BERT with Adaptive Inference Time,北京大学,腾讯

https://arxiv.org/pdf/2004.02178.pdf

0 人点赞