cs.CL 方向，今日共计30篇

BERT(1篇)

【1】 BertGCN: Transductive Text Classification by Combining GCN and BERT
标题：BertGCN：结合GCN和BERT的感应式文本分类
作者：Yuxiao Lin,Yuxian Meng,Xiaofei Sun,Qinghong Han,Kun Kuang,Jiwei Li,Fei Wu
机构：♠Computer Science Department, Zhejiang University, ♣ ShannonAI
链接：https://arxiv.org/abs/2105.05727

 

QA|VQA|问答|对话(2篇)

【1】 Building a Question and Answer System for News Domain
标题：构建新闻领域的问答系统
作者：Sandipan Basu,Aravind Gaddala,Pooja Chetan,Garima Tiwari,Narayana Darapaneni,Sadwik Parvathaneni,Anwesh Reddy Paduri
机构：Director – AIML, Great LearningNorthwestern, University Illinois, USA, Student – AIML, Bangalore, India, Mentor– AIML, Anwesh  Reddy Paduri, Data Scientist - AIML
链接：https://arxiv.org/abs/2105.05744

【2】 Encoding Explanatory Knowledge for Zero-shot Science Question Answering
标题：零命中式科学答疑的解释性知识编码
作者：Zili Zhou,Marco Valentino,Donal Landers,Andre Freitas
机构：Department of Computer Science, University of Manchester, United Kingdom, Digital Experimental Cancer Medicine Team, Cancer Research UK Manchester Institute, United Kingdom, Idiap Research Institute, Switzerland
链接：https://arxiv.org/abs/2105.05737

 

机器翻译(2篇)

【1】 Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained  Models into Speech Translation Encoders
标题：堆叠式声学和文本编码：将预先训练的模型集成到语音翻译编码器中
作者：Chen Xu,Bojie Hu,Yanyang Li,Yuhao Zhang,shen huang,Qi Ju,Tong Xiao,Jingbo Zhu
机构：NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China, Tencent Minority-Mandarin Translation, Beijing, China, The Chinese University of Hong Kong, Hong Kong, China, NiuTrans Research, Shenyang, China
备注：ACL 2021
链接：https://arxiv.org/abs/2105.05752

【2】 Improving Lexically Constrained Neural Machine Translation with  Source-Conditioned Masked Span Prediction
标题：源条件掩蔽跨度预测改进词汇约束神经机器翻译
作者：Gyubok Lee,Seongjun Yang,Edward Choi
机构：Graduate School of AI, KAIST
备注：To appear in ACL 2021
链接：https://arxiv.org/abs/2105.05498

 

语义分析(2篇)

【1】 The Semantic Brand Score
标题：语义品牌得分
作者：A Fronzetti Colladon
备注：None
链接：https://arxiv.org/abs/2105.05781

【2】 Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and  Semantic Embedding
标题：基于概率推理和语义嵌入的无监督知识图对齐
作者：Zhiyuan Qi,Ziheng Zhang,Jiaoyan Chen,Xi Chen,Yuejia Xiang,Ningyu Zhang,Yefeng Zheng
机构：Tencent Jarvis Lab, Shenzhen, China, Department of Computer Science, University of Oxford, UK, Platform and Content Group, Tencent, Shenzhen, China, Zhejiang University, Hangzhou, China
备注：Accepted by IJCAI 2021
链接：https://arxiv.org/abs/2105.05596

 

Graph|知识图谱|Knowledge(3篇)

【1】 NLP for Climate Policy: Creating a Knowledge Platform for Holistic and  Effective Climate Action
标题：气候政策NLP：为全面和有效的气候行动创建知识平台
作者：Pradip Swarnakar,Ashutosh Modi
机构：Department of Humanities and Social Sciences, Department of Computer Science and Engineering, Indian Institute of Technology Kanpur, Kanpur , India
备注：12 Pages (8 + 4 pages for references)
链接：https://arxiv.org/abs/2105.05621

【2】 Incorporating Commonsense Knowledge Graph in Pretrained Models for  Social Commonsense Tasks
标题：将常识知识图纳入社会常识任务的预训练模型
作者：Ting-Yun Chang,Yang Liu,Karthik Gopalakrishnan,Behnam Hedayatnia,Pei Zhou,Dilek Hakkani-Tur
机构：Academia Sinica, Taiwan;,  Alexa AI, Amazon, USA;,  USC, USA
备注：EMNLP2020 Workshop
链接：https://arxiv.org/abs/2105.05457

【3】 Could you give me a hint? Generating inference graphs for defeasible  reasoning
标题：你能给我一个提示吗？生成用于可废止推理的推理图
作者：Aman Madaan,Dheeraj Rajagopal,Niket Tandon,Yiming Yang,Eduard Hovy
机构：Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA, † Allen Institute for Artificial Intelligence, Seattle, WA, USA
备注：Findings of the Association for Computational Linguistics: ACL 2021
链接：https://arxiv.org/abs/2105.05418

 

摘要|信息提取(1篇)

【1】 Kleister: Key Information Extraction Datasets Involving Long Documents  with Complex Layouts
标题：Kleister：涉及具有复杂布局的长文档的关键信息提取数据集
作者：Tomasz Stanisławek,Filip Graliński,Anna Wróblewska,Dawid Lipiński,Agnieszka Kaliska,Paulina Rosalska,Bartosz Topolski,Przemysław Biecek
机构：Warsaw University of Technology, Koszykowa , Warsaw, Poland,  Adam Mickiewicz University, Wieniawskiego, Poznan, Poland,  Samsung R&D Institute Poland, Plac Europejski , Warsaw, Poland
备注：accepted to ICDAR 2021
链接：https://arxiv.org/abs/2105.05796

 

推理|分析|理解|解释(1篇)

【1】 Evaluating Gender Bias in Natural Language Inference
标题：评估自然语言推理中的性别偏见
作者：Shanya Sharma,Manan Dey,Koustuv Sinha
机构：Walmart Labs, SAP Labs, Quebec Artifical Intelligence Institute (Mila), McGill University, Facebook AI Research
备注：NeurIPS 2020 Workshop on Dataset Curation and Security
链接：https://arxiv.org/abs/2105.05541

 

GAN|对抗|攻击|生成相关(1篇)

【1】 OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection  with Natural Language Attack
标题：OutFlip：自然语言攻击下未知意图检测的域外样本生成
作者：DongHyun Choi,Myeong Cheol Shin,EungGyun Kim,Dong Ryeol Shin
机构：Kakao Enterprise, Pangyo, South Korea, Sungkyunkwan University, Suwon, South Korea
备注：9 pages, 3 figures; to be appear in ACL Findings of ACL-IJCNLP 2021
链接：https://arxiv.org/abs/2105.05601

 

检测相关(1篇)

【1】 !Qué maravilla! Multimodal Sarcasm Detection in Spanish: a Dataset and  a Baseline
标题：！奎马拉维拉！西班牙语中的多模态讽刺检测：数据集和基线
作者：Khalid Alnajjar,Mika Hämäläinen
机构：Department of Digital Humanities, University of Helsinki
备注：Accepted to The Third Workshop on Multimodal Artificial Intelligence (MAI-Workshop)
链接：https://arxiv.org/abs/2105.05542

 

识别/分类(2篇)

【1】 Priberam at MESINESP Multi-label Classification of Medical Texts Task
标题：MESINESP医学文本多标签分类任务中的Priberam
作者：Ruben Cardoso,Zita Marinho,Afonso Mendes,Sebastião Miranda
机构：Priberam Labs, Lisbon, Portugal
备注：Presented at CLEF2020 conference (2020)
链接：https://arxiv.org/abs/2105.05614

【2】 Priberam Labs at the NTCIR-15 SHINRA2020-ML: Classification Task
标题：NTCIR-15 SHINRA2020-ML的Priberam实验室：分类任务
作者：Ruben Cardoso,Afonso Mendes,Andre Lamurias
机构：Priberam Labs, Portugal
备注：Presented at NTCIR-15 conference (2020)
链接：https://arxiv.org/abs/2105.05605

 

检索(1篇)

【1】 Yes, BM25 is a Strong Baseline for Legal Case Retrieval
标题：是的，BM25是法律案例检索的强大基线
作者：Guilherme Moraes Rosa,Ruan Chaves Rodrigues,Roberto Lotufo,Rodrigo Nogueira
机构：NeuralMind, University of Campinas (Unicamp), Federal University of Goiás (UFG), Roberto de Alencar Lotufo, University of Waterloo
链接：https://arxiv.org/abs/2105.05686

 

表征(1篇)

【1】 Discrete representations in neural models of spoken language
标题：口语神经模型中的离散表示
作者：Bertrand Higy,Lieke Gelderloos,Afra Alishahi,Grzegorz Chrupała
机构：Cognitive Science and AI, Tilburg University
链接：https://arxiv.org/abs/2105.05582

 

其他神经网络|深度学习|模型|建模(4篇)

【1】 How Reliable are Model Diagnostics?
标题：模型诊断的可靠性如何？
作者：Vamsi Aribandi,Yi Tay,Donald Metzler
机构：Google Research
备注：ACL 2021 Findings
链接：https://arxiv.org/abs/2105.05641

【2】 Probabilistic modelling of rational communication with conditionals
标题：条件句理性交流的概率建模
作者：Britta Grusdt,Daniel Lassiter,Michael Franke
机构：Institute of Cognitive Science, University of Osnabrück, Department of Linguistics, Stanford University
链接：https://arxiv.org/abs/2105.05502

【3】 UIUC_BioNLP at SemEval-2021 Task 11: A Cascade of Neural Models for  Structuring Scholarly NLP Contributions
标题：UIUC_BioNLP在SemEval-2021年任务11：构建学术NLP投稿的一系列神经模型
作者：Haoyang Liu,M. Janina Sarol,Halil Kilicoglu
机构：School of Information Sciences, University of Illinois at Urbana-Champaign
链接：https://arxiv.org/abs/2105.05435

【4】 The Summary Loop: Learning to Write Abstractive Summaries Without  Examples
标题：摘要循环：学习在没有示例的情况下编写摘要
作者：Philippe Laban,Andrew Hsi,John Canny,Marti A. Hearst
机构：Bloomberg, UC Berkeley∗
备注：ACL2020, 16 pages, 9 figures
链接：https://arxiv.org/abs/2105.05361

 

其他(8篇)

【1】 The Greedy and Recursive Search for Morphological Productivity
标题：形态生产力的贪婪递归搜索
作者：Caleb Belth,Sarah Payne,Deniz Beser,Jordan Kodner,Charles Yang
机构：Department of Computer Science and Engineering, University of Michigan, Department of Linguistics and Department of Computer and Information Science, University of Pennsylvania, Information Sciences Institute, University of Southern California
备注：CogSci 2021
链接：https://arxiv.org/abs/2105.05790

【2】 Forecasting election results by studying brand importance in online news
标题：通过研究网络新闻中的品牌重要性来预测选举结果
作者：A. Fronzetti Colladon
备注：None
链接：https://arxiv.org/abs/2105.05762

【3】 Conversational Negation using Worldly Context in Compositional  Distributional Semantics
标题：组合分布语义学中使用世俗语境的会话否定
作者：Benjamin Rodatz,Razin A. Shaikh,Lia Yeh
机构：Computer Science, University of Oxford, benjamin.rodatz, Mathematical Institute, razin.shaikh, All authors have contributed equally., Quantum Group
备注：13 pages, 5 figures, To be published in Proceedings of SEMSPACE 2021 and to appear in the ACL anthology
链接：https://arxiv.org/abs/2105.05748

【4】 "Alexa, what do you do for fun?" Characterizing playful requests with  virtual assistants
作者：Chen Shani,Alexander Libov,Sofia Tolmach,Liane Lewin-Eytan,Yoelle Maarek,Dafna Shahaf
机构：The Hebrew University of Jerusalem, Amazon Alexa Shopping
链接：https://arxiv.org/abs/2105.05571

【5】 Mining Legacy Issues in Open Pit Mining sites: Innovation & Support of  Renaturalization and Land Utilization
标题：露天矿场采矿遗产问题：土地复垦与利用的创新与支撑
作者：Christopher Schröder,Kim Bürgl,Yves Annanias,Andreas Niekler,Lydia Müller,Daniel Wiegreffe,Christian Bender,Christoph Mengs,Gerik Scheuermann,Gerhard Heyer
机构：Natural Language Processing Group, Leipzig University, Image and Signal Processing Group, Institute of Public Finance and Public Management
链接：https://arxiv.org/abs/2105.05557

【6】 OCHADAI-KYODAI at SemEval-2021 Task 1: Enhancing ModelGeneralization and  Robustness for Lexical Complexity Prediction
标题：OCHADAI-kyodai在SemEval-2021年任务1：增强词汇复杂性预测的模型泛化和稳健性
作者：Yuki Taya,Lis Kanashiro Pereira,Fei Cheng,Ichiro Kobayashi
机构：Ochanomizu University, Japan, Kyoto University, Japan
链接：https://arxiv.org/abs/2105.05535

【7】 What's The Latest? A Question-driven News Chatbot
标题：有什么最新消息吗？一种问题驱动的新闻聊天机器人
作者：Philippe Laban,John Canny,Marti A. Hearst
机构：UC Berkeley
备注：ACL2020 Demo Track, 8 pages, 5 figures
链接：https://arxiv.org/abs/2105.05392

【8】 News Headline Grouping as a Challenging NLU Task
标题：新闻标题分组是一项具有挑战性的自然语言理解任务
作者：Philippe Laban,Lucas Bandarkar,Marti A. Hearst
机构：UC Berkeley
备注：NAACL2021, 13 pages, 8 figures
链接：https://arxiv.org/abs/2105.05391