自然语言处理（1月26日更新版） 

[1] PAWLS: PDF Annotation With Labels and Structure

作者 | Mark Neumann, Zejiang Shen, Sam Skjonsberg

链接 | https://arxiv.org/abs/2101.10281 

[2] TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics

作者 | Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, Debasis Ganguly

链接 | https://arxiv.org/abs/2101.10273 

备注 | accepted at EACL 2021

[3] Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale

作者 | Gabriella Skitalinskaya, Jonas Klaff, Henning Wachsmuth

链接 | https://arxiv.org/abs/2101.10250 

备注 | Accepted as a long paper at EACL 2021

[4] Process-Level Representation of Scientific Protocols with Interactive Annotation

作者 | Ronen Tamari, Fan Bai, Alan Ritter, Gabriel Stanovsky

链接 | https://arxiv.org/abs/2101.10244 

项目链接 | https://textlabs.github.io/

备注 | Accepted to EACL 2021. 

[5] A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction

作者 | Yongliang Shen, Xinyin Ma, Yechun Tang, Weiming Lu

链接 | https://arxiv.org/abs/2101.10213 

[6] A Hybrid Approach to Measure Semantic Relatedness in Biomedical Concepts

作者 | Katikapalli Subramanyam Kalyan, Sivanesan Sangeetha

链接 | https://arxiv.org/abs/2101.10196 

备注 | preprint under review

[7] Open-Mindedness and Style Coordination in Argumentative Discussions

作者 | Aviv Ben Haim, Oren Tsur

链接 | https://arxiv.org/abs/2101.10164 

[8] With Measured Words: Simple Sentence Selection for Black-Box Optimization of Sentence Compression Algorithms

作者 | Yotam Shichel, Meir Kalech, Oren Tsur

链接 | https://arxiv.org/abs/2101.10096 

[9] RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding

作者 | Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi

链接 | https://arxiv.org/abs/2101.10070 

备注 | Accepted in EACL 2021

[10] Cross-lingual Visual Pre-training for Multimodal Machine Translation

作者 | Ozan Caglayan, Menekse Kuyu, Mustafa Sercan Amac, Pranava Madhyastha, Erkut Erdem, Aykut Erdem, Lucia Specia

链接 | https://arxiv.org/abs/2101.10044 

备注 | Accepted to EACL 2021 (Camera-ready version)

[11] SpanEmo: Casting Multi-label Emotion Classification as Span-prediction

作者 | Hassan Alhuzali, Sophia Ananiadou

链接 | https://arxiv.org/abs/2101.10038 

备注 | accepted at EACL2021

[12] Facilitating Terminology Translation with Target Lemma Annotations

作者 | Toms Bergmanis, Mārcis Pinnis

链接 | https://arxiv.org/abs/2101.10035 

备注 | accepted for EACL

[13] A Simple Disaster-Related Knowledge Base for Intelligent Agents

作者 | Clark Emmanuel Paulo, Arvin Ken Ramirez, David Clarence Reducindo, Rannie Mark Mateo, Joseph Marvin Imperial

链接 | https://arxiv.org/abs/2101.10014 

备注 | 7 tables, 1 figure, presented at 34th Pacific Asia Conference on Language, Information and Computation

[14] Unsupervised Key-phrase Extraction and Clustering for Classification Scheme in Scientific Publications

作者 | Xiajing Li, Marios Daoutis

链接 | https://arxiv.org/abs/2101.09990 

备注 | Accepted to SDU@AAAI 2021 workshop

[15] CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

作者 | Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang', Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann

链接 | https://arxiv.org/abs/2101.09969 

备注 | accepted in EACL 2021 (full paper)

[16] EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information

作者 | Lei Huang, Jiecong Lin, Xiangtao Li, Linqi Song, Ka-Chun Wong

链接 | https://arxiv.org/abs/2101.09914 

[17] GP: Context-free Grammar Pre-training for Text-to-SQL Parsers

作者 | Liang Zhao, Hexin Cao, Yunsong Zhao

链接 | https://arxiv.org/abs/2101.09901 

[18] MadDog: A Web-based System for Acronym Identification and Disambiguation

作者 | Amir Pouran Ben Veyseh, Franck Dernoncourt, Walter Chang, Thien Huu Nguyen

链接 | https://arxiv.org/abs/2101.09893 

[19] FakeFlow: Fake News Detection by Modeling the Flow of Affective Information

作者 | Bilal Ghanem, Simone Paolo Ponzetto, Paolo Rosso, Francisco Rangel

链接 | https://arxiv.org/abs/2101.09810 

备注 | EACL-2021

[20] Evaluating Models of Robust Word Recognition with Serial Reproduction

作者 | Stephan C. Meylan, Sathvik Nair, Thomas L. Griffiths

链接 | https://arxiv.org/abs/2101.09788 

[21] Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks

作者 | Hongyin Luo, Shang-Wen Li, James Glass

链接 | https://arxiv.org/abs/2101.09773 

备注 | Appears in the Proceedings of the 3rd Clinical Natural Language Processing Workshop

[22] Belief-based generation of Argumentative Claims

作者 | Milad Alshomary, Wei-Fan Chen, Timon Gurcke, Henning Wachsmuth

链接 | https://arxiv.org/abs/2101.09765 

备注 | Almost 9 pages, 1 figure, EACL-21 paper

[23] RomeBERT: Robust Training of Multi-Exit BERT

作者 | Shijie Geng, Peng Gao, Zuohui Fu, Yongfeng Zhang

链接 | https://arxiv.org/abs/2101.09755 

[24] A Novel Two-stage Framework for Extracting Opinionated Sentences from News Articles

作者 | Rajkumar Pujari, Swara Desai, Niloy Ganguly, Pawan Goyal

链接 | https://arxiv.org/abs/2101.09743 

备注 | Presented as a talk at TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing at EMNLP 2014

[25] Does Head Label Help for Long-Tailed Multi-Label Text Classification

作者 | Lin Xiao, Xiangliang Zhang, Liping Jing, Chi Huang, Mingyang Song

链接 | https://arxiv.org/abs/2101.09704 

备注 | Accepted by AAAI2021

[26] Fast Sequence Generation with Multi-Agent Reinforcement Learning

作者 | Longteng Guo, Jing Liu, Xinxin Zhu, Hanqing Lu

链接 | https://arxiv.org/abs/2101.09698 

备注 | arXiv admin note: substantial text overlap with arXiv:2005.04690

[27] A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks

作者 | Mohsen Ahmadzadeh, Mehdi Kamal, Ali Afzali-Kusha, Massoud Pedram

链接 | https://arxiv.org/abs/2101.09693 

[28] Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models

作者 | Daniel de Vassimon Manela, David Errington, Thomas Fisher, Boris van Breugel, Pasquale Minervini

链接 | https://arxiv.org/abs/2101.09688 

备注 | Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)

[29] Does Dialog Length matter for Next Response Selection task? An Empirical Study

作者 | Jatin Ganhotra, Sachindra Joshi

链接 | https://arxiv.org/abs/2101.09647 

[30] WangchanBERTa: Pretraining transformer-based Thai Language Models

作者 | Lalita Lowphansirikul, Charin Polpanumas, Nawat Jantrakulchai, Sarana Nutanong

链接 | https://arxiv.org/abs/2101.09635 

[31] On the Evolution of Word Order

作者 | Idan Rejwan, Avi Caciularu

链接 | https://arxiv.org/abs/2101.09579 

[32] Dictionary-based Debiasing of Pre-trained Word Embeddings

作者 | Masahiro Kaneko, Danushka Bollegala

链接 | https://arxiv.org/abs/2101.09525 

备注 | EACL 2021

[33] Debiasing Pre-trained Contextualised Embeddings

作者 | Masahiro Kaneko, Danushka Bollegala

链接 | https://arxiv.org/abs/2101.09523 

备注 | EACL 2021

[34] Training Multilingual Pre-trained Language Model with Byte-level Subwords

作者 | Junqiu Wei, Qun Liu, Yinpeng Guo, Xin Jiang

链接 | https://arxiv.org/abs/2101.09469 

[35] WebSRC: A Dataset for Web-Based Structural Reading Comprehension

作者 | Lu Chen, Xingyu Chen, Zihan Zhao, Danyang Zhang, Jiabao Ji, Ao Luo, Yuxuan Xiong, Kai Yu

链接 | https://arxiv.org/abs/2101.09465 

[36] ARTH: Algorithm For Reading Text Handily -- An AI Aid for People having Word Processing Issues

作者 | Akanksha Malhotra, Sudhir Kamle

链接 | https://arxiv.org/abs/2101.09464 

[37] Reproducibility, Replicability and Beyond: Assessing Production Readiness of Aspect Based Sentiment Analysis in the Wild

作者 | Rajdeep Mukherjee, Shreyas Shetty, Subrata Chattopadhyay, Subhadeep Maji, Samik Datta, Pawan Goyal

链接 | https://arxiv.org/abs/2101.09449 

备注 | accepted at ECIR 2021

[38] Towards Natural Language Question Answering over Earth Observation Linked Data using Attention-based Neural Machine Translation

作者 | Abhishek V. Potnis, Rajat C. Shinde, Surya S. Durbha

链接 | https://arxiv.org/abs/2101.09427 

备注 | Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2020

[39] Analyzing Team Performance with Embeddings from Multiparty Dialogues

作者 | Ayesha Enayet, Gita Sukthankar

链接 | https://arxiv.org/abs/2101.09421 

备注 | To be published in the 15th IEEE International Conference on Semantic Computing

[40] Slot Self-Attentive Dialogue State Tracking

作者 | Fanghua Ye, Jarana Manotumruksa, Qiang Zhang, Shenghui Li, Emine Yilmaz

链接 | https://arxiv.org/abs/2101.09374 

备注 | to appear at The Web Conference (WWW) 2021

[41] Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection

作者 | Jens Kaiser, Sinan Kurtyigit, Serge Kotchourko, Dominik Schlechtweg

链接 | https://arxiv.org/abs/2101.09368 

[42] BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets

作者 | Fouzi Harrag, Maria Debbah, Kareem Darwish, Ahmed Abdelali

链接 | https://arxiv.org/abs/2101.09345 

[43] k-Neighbor Based Curriculum Sampling for Sequence Prediction

作者 | James O' Neill, Danushka Bollegala

链接 | https://arxiv.org/abs/2101.09313 

备注 | arXiv admin note: substantial text overlap with arXiv:1809.05916

[44] Drug and Disease Interpretation Learning with Biomedical Entity Representation Transformer

作者 | Zulfat Miftahutdinov, Artur Kadurin, Roman Kudrin, Elena Tutubalina

链接 | https://arxiv.org/abs/2101.09311 

备注 | Accepted to the 43rd European Conference on Information Retrieval (ECIR 2021)

[45] Censorship of Online Encyclopedias: Implications for NLP Models

作者 | Eddie Yang, Margaret E. Roberts

链接 | https://arxiv.org/abs/2101.09294 

备注 | Accepted for publication at ACM FAccT 2021

[46] The emergence of visual semantics through communication games

作者 | Daniela Mihai, Jonathon Hare

链接 | https://arxiv.org/abs/2101.10253 

备注 | arXiv admin note: text overlap with arXiv:1911.05546

[47] MICROS: Mixed-Initiative ConveRsatiOnal Systems Workshop

作者 | Ida Mele, Cristina Ioana Muntean, Mohammad Aliannejadi, Nikos Voskarides

链接 | https://arxiv.org/abs/2101.10219 

备注 | ECIR 2021 workshop

[48] Fringe News Networks: Dynamics of US News Viewership following the 2020 Presidential Election

作者 | Ashiqur R. KhudaBukhsh, Rupak Sarkar, Mark S. Kamlet, Tom M. Mitchell

链接 | https://arxiv.org/abs/2101.10112 

[49] Re-imagining Algorithmic Fairness in India and Beyond

作者 | Nithya Sambasivan, Erin Arnesen, Ben Hutchinson, Tulsee Doshi, Vinodkumar Prabhakaran

链接 | https://arxiv.org/abs/2101.09995 

[50] ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning

作者 | Yufei Wang, Ian D. Wood, Stephen Wan, Mark Johnson

链接 | https://arxiv.org/abs/2101.09865 

备注 | long paper accepted @ EACL-2021 camera ready version

[51] Analysing the Noise Model Error for Realistic Noisy Label Data

作者 | Michael A. Hedderich, Dawei Zhu, Dietrich Klakow

链接 | https://arxiv.org/abs/2101.09763 

项目链接 | https://github.com/uds-lsv/noise-estimation

备注 | Accepted at AAAI 2021

[52] Automatic Monitoring Social Dynamics During Big Incidences: A Case Study of COVID-19 in Bangladesh

作者 | Fahim Shahriar, Md Abul Bashar

链接 | https://arxiv.org/abs/2101.09667 

[53] Explanation as a Defense of Recommendation

作者 | Aobo Yang, Nan Wang, Hongbo Deng, Hongning Wang

链接 | https://arxiv.org/abs/2101.09656 

备注 | WSDM 2021

[54] A Review of Speaker Diarization: Recent Advances with Deep Learning

作者 | Tae Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis, Kyu J. Han, Shinji Watanabe, Shrikanth Narayanan

链接 | https://arxiv.org/abs/2101.09624 

[55] Advances and Challenges in Conversational Recommender Systems: A Survey

作者 | Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, Tat-Seng Chua

链接 | https://arxiv.org/abs/2101.09459