每日论文速递:自然语言处理相关(11月1日更新版)

作者:Hsu
转载自:深度学习这件小事
原文链接:

自然语言处理(11月1日更新版)

[1] MetaICL: Learning to Learn In Context作者 | Sewon Min, Mike Lewis, Luke Zettlemoyer, Hannaneh Hajishirzi链接 | arxiv.org/abs/2110.1594 项目链接 | github.com/facebookrese

[2] Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence作者 | Letian Peng, Zuchao Li, Hai Zhao链接 | arxiv.org/abs/2110.1593

[3] Transformer Ensembles for Sexism Detection作者 | Lily Davies, Marta Baldracchi, Carlo Alessandro Borella, Konstantinos Perifanos链接 | arxiv.org/abs/2110.1590

[4] From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey作者 | Enrica Troiano, Aswathy Velutharambath, and Roman Klinger链接 | arxiv.org/abs/2110.1587 备注 | 58 pages, 2 figures, 9 tables. Submitted for review to the Journal of Natural Language Engineering, Cambridge University Press

[5] Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition作者 | Chak-Fai Li, Francis Keith, William Hartmann, Matthew Snover链接 | arxiv.org/abs/2110.1583 备注 | 5 pages

[6] Natural Language Processing for Smart Healthcare作者 | Binggui Zhou, Guanghua Yang, Zheng Shi, Shaodan Ma链接 | arxiv.org/abs/2110.1580

[7] BERMo: What can BERT learn from ELMo?作者 | Sangamesh Kodge, Kaushik Roy链接 | arxiv.org/abs/2110.1580

[8] Application of the Multi-label Residual Convolutional Neural Network text classifier using Content-Based Routing process作者 | Tounsi Achraf, Elkefi Safa链接 | arxiv.org/abs/2110.1580 备注 | 4 pages, 4 figures

[9] Discovering Non-monotonic Autoregressive Orderings with Variational Inference作者 | Xuanlin Li, Brandon Trabucco, Dong Huk Park, Michael Luo, Sheng Shen, Trevor Darrell, Yang Gao链接 | arxiv.org/abs/2110.1579 备注 | updated from ICLR 2021, first two authors contributed equally

[10] CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring作者 | Vinay Aggarwal, Aparna Garimella, Balaji Vasan Srinivasan, Anandhavelu N, Rajiv Jain链接 | arxiv.org/abs/2110.1579

[11] Comparing Machine Learning-Centered Approaches for Forecasting Language Patterns During Frustration in Early Childhood作者 | Arnav Bhakta, Yeunjoo Kim, Pamela Cole链接 | arxiv.org/abs/2110.1577 备注 | 9 pages, 6 figures, UNDER REVIEW, UNPUBLISHED

[12] NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM作者 | Connor Holmes, Minjia Zhang, Yuxiong He, Bo Wu链接 | arxiv.org/abs/2110.1576

[13] How to Leverage Multimodal EHR Data for Better Medical Predictions?作者 | Bo Yang, Lijun Wu链接 | arxiv.org/abs/2110.1576 备注 | Accepted by EMNLP 2021

[14] Detecting Gender Bias in Transformer-based Models: A Case Study on BERT作者 | Bingbing Li, Hongwu Peng, Rajat Sainju, Junhuan Yang, Lei Yang, Yueying Liang, Weiwen Jiang, Binghui Wang, Hang Liu, Caiwen Ding链接 | arxiv.org/abs/2110.1573

[15] Named Entity Recognition in Unstructured Medical Text Documents作者 | Cole Pearson, Naeem Seliya, Rushit Dave链接 | arxiv.org/abs/2110.1573

[16] CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese作者 | Arnaldo Candido Junior, Edresson Casanova, Anderson Soares, Frederico Santos de Oliveira, Lucas Oliveira, Ricardo Corso Fernandes Junior, Daniel Peixoto Pinto da Silva, Fernando Gorgulho Fayet, Bruno Baldissera Carlotto, Lucas Rafael Stefanel Gris, Sandra Maria Aluísio链接 | arxiv.org/abs/2110.1573 备注 | This paper is under consideration at Language Resources and Evaluation (LREV)

[17] E-Commerce Dispute Resolution Prediction作者 | David Tsurel, Michael Doron, Alexander Nus, Arnon Dagan, Ido Guy, Dafna Shahaf链接 | arxiv.org/abs/2110.1573

[18] Deep Learning for Bias Detection: From Inception to Deployment作者 | Md Abul Bashar, Richi Nayak, Anjor Kothare, Vishal Sharma, Kesavan Kandadai链接 | arxiv.org/abs/2110.1572

[19] Calling to CNN-LSTM for Rumor Detection: A Deep Multi-channel Model for Message Veracity Classification in Microblogs作者 | Abderrazek Azri (ERIC), Cécile Favre (ERIC), Nouria Harbi (ERIC), Jérôme Darmont (ERIC), Camille Noûs链接 | arxiv.org/abs/2110.1572

[20] Social Media Reveals Urban-Rural Differences in Stress across China作者 | Jesse Cui, Tingdan Zhang, Dandan Pang, Kokil Jaidka, Garrick Sherman, Vinit Jakhetiya, Lyle Ungar, Sharath Chandra Guntuku链接 | arxiv.org/abs/2110.1572 备注 | Accepted at AAAI Conference on Web and Social Media (ICWSM) 2022

[21] Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks作者 | Anton Chernyavskiy, Dmitry Ilvovsky, Pavel Kalinin, Preslav Nakov链接 | arxiv.org/abs/2110.1572 备注 | batch-softmax contrastive loss, pairwise sentence scoring, classification, ranking, and regression

[22] Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks作者 | Janarthanan Rajendran, Jonathan K. Kummerfeld, Satinder Singh链接 | arxiv.org/abs/2110.1572 备注 | Workshop on NLP for Conversational AI, EMNLP 2021

[23] SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation作者 | Tuan Nguyen, Hanh Pham, Truong Bui, Tan Nguyen, Duc Luong, Phong Nguyen链接 | arxiv.org/abs/2110.1572

[24] A Novel Sequence Tagging Framework for Consumer Event-Cause Extraction作者 | Congqing He, Jie Zhang, Xiangyu Zhu, Huan Liu, Yukun Huang链接 | arxiv.org/abs/2110.1572

[25] Paperswithtopic: Topic Identification from Paper Title Only作者 | Daehyun Cho, Christian Wallraven链接 | arxiv.org/abs/2110.1572

[26] Weakly Supervised Concept Map Generation through Task-Guided Graph Translation作者 | Jiaying Lu, Xiangjue Dong, Carl J. Yang链接 | arxiv.org/abs/2110.1572

[27] Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text作者 | Mai A. Shaaban (1), Yasser F. Hassan (2), Shawkat K. Guirguis (3) ((1) Department of Mathematics and Computer Science, Faculty of Science, Alexandria University, Alexandria, Egypt, (2) Faculty of Computers and Data Science, Alexandria University, Alexandria, Egypt, (3) Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt)链接 | arxiv.org/abs/2110.1571

[28] LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network作者 | Vibhav Agarwal, Sudeep Deepak Shivnikar, Sourav Ghosh, Himanshu Arora, Yashwant Saini链接 | arxiv.org/abs/2110.1571 备注 | Accepted for publication in 2021 IEEE 20th International Conference on Machine Learning and Applications (ICMLA)

[29] Building the Language Resource for a Cebuano-Filipino Neural Machine Translation System作者 | Kristine Mae Adlaon, Nelson Marcos链接 | arxiv.org/abs/2110.1571 备注 | Published in the Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval. arXiv admin note: substantial text overlap with arXiv:1902.07250

[30] Analysing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets作者 | Changchang. Zeng, Shaobo. Li链接 | arxiv.org/abs/2110.1571

[31] Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus作者 | Sohrab Ferdowsi, Nikolay Borissov, Julien Knafou, Poorya Amini, Douglas Teodoro链接 | arxiv.org/abs/2110.1571 备注 | Accepted as a long paper in EMNLP 2021 - Oral presentation to the Machine Learning track

[32] LegalNLP -- Natural Language Processing methods for the Brazilian Legal Language作者 | Felipe Maia Polo, Gabriel Caiaffa Floriano Mendonça, Kauê Capellato J. Parreira, Lucka Gianvechio, Peterson Cordeiro, Jonathan Batista Ferreira, Leticia Maria Paz de Lima, Antônio Carlos do Amaral Maia, Renato Vicente链接 | arxiv.org/abs/2110.1570

[33] Neural sentence embedding models for semantic similarity estimation in the biomedical domain作者 | Kathrin Blagec, Hong Xu, Asan Agibetov, Matthias Samwald链接 | arxiv.org/abs/2110.1570 备注 | Abstract shortened to comply with arXiv guidelines

[34] Hidden Markov Based Mathematical Model dedicated to Extract Ingredients from Recipe Text作者 | Zied Baklouti (UP, ENIT)链接 | arxiv.org/abs/2110.1570

[35] Integrating Deep Event-Level and Script-Level Information for Script Event Prediction作者 | Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng链接 | arxiv.org/abs/2110.1570 备注 | EMNLP 2021 long paper (main conference)

[36] Distilling Relation Embeddings from Pre-trained Language Models作者 | Asahi Ushio, Jose Camacho-Collados, Steven Schockaert链接 | arxiv.org/abs/2110.1570 备注 | EMNLP 2021 main conference

[37] Influence of ASR and Language Model on Alzheimer's Disease Detection作者 | Joan Codina-Filbà, Guillermo Cámbara, Jordi Luque, Mireia Farrús链接 | arxiv.org/abs/2110.1570 备注 | 5 pages. Submitted to Interspeech 2021. arXiv admin note: text overlap with arXiv:2011.09272

[38] Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning作者 | Yuanzhi Chen, Mohammad Rashedul Hasan链接 | arxiv.org/abs/2110.1570 备注 | The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)

[39] Overview of ADoBo 2021: Automatic Detection of Unassimilated Borrowings in the Spanish Press作者 | Elena Álvarez Mellado, Luis Espinosa Anke, Julio Gonzalo Arroyo, Constantine Lignos, Jordi Porta Zamorano链接 | arxiv.org/abs/2110.1568 备注 | Post-print. Original version at Procesamiento del Lenguaje Natural 67 (2021), p. 277-285

[40] Amendable Generation for Dialogue State Tracking作者 | Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao, Huang He, Yunyi Yang, Hua Wu, Fan Wang, Shuqi Sun链接 | arxiv.org/abs/2110.1565 备注 | Presented at EMNLP 2021 NLP4ConvAI Workshop

[41] Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings作者 | Guanglin Niu, Yang Li, Chengguang Tang, Zhongkai Hu, Shibin Yang, Peng Li, Chengyu Wang, Hao Wang, Jian Sun链接 | arxiv.org/abs/2110.1562

[42] MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare作者 | Shaoxiong Ji, Tianlin Zhang, Luna Ansari, Jie Fu, Prayag Tiwari, Erik Cambria链接 | arxiv.org/abs/2110.1562

[43] Handshakes AI Research at CASE 2021 Task 1: Exploring different approaches for multilingual tasks作者 | Vivek Kalyan, Paul Tan, Shaun Tan, Martin Andrews链接 | arxiv.org/abs/2110.1559 备注 | Accepted paper for CASE 2021 workshop at ACL-IJCNLP 2021. (6 pages including references)

[44] Automatic Hand Sign Recognition: Identify Unusuality through Latent Cognizance作者 | Pisit Nakjai, Tatpong Katanyukul链接 | arxiv.org/abs/2110.1554 备注 | 12 pages

[45] Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing作者 | Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Young-Suk Lee, Radu Florian, Salim Roukos链接 | arxiv.org/abs/2110.1553 备注 | EMNLP 2021 main conference

[46] Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model作者 | Liang He, Shizhuo Zhang, Lijun Wu, Huanhuan Xia, Fusong Ju, He Zhang, Siyuan Liu, Yingce Xia, Jianwei Zhu, Pan Deng, Bin Shao, Tao Qin, Tie-Yan Liu链接 | arxiv.org/abs/2110.1552

[47] Learning Personal Food Preferences via Food Logs Embedding作者 | Ahmed A. Metwally, Ariel K. Leong, Aman Desai, Anvith Nagarjuna, Dalia Perelman, Michael Snyder链接 | arxiv.org/abs/2110.1549

[48] Using Text Analytics for Health to Get Meaningful Insights from a Corpus of COVID Scientific Papers作者 | Dmitry Soshnikov, Vickie Soshnikova链接 | arxiv.org/abs/2110.1545 备注 | 13 pages, 11 figures

[49] What makes us curious? analysis of a corpus of open-domain questions作者 | Zhaozhen Xu, Amelia Howarth, Nicole Briggs, Nello Cristianini链接 | arxiv.org/abs/2110.1540

[50] Visual Keyword Spotting with Attention作者 | K R Prajwal, Liliane Momeni, Triantafyllos Afouras, Andrew Zisserman链接 | arxiv.org/abs/2110.1595 备注 | Appears in: British Machine Vision Conference 2021 (BMVC 2021)

[51] Guided Policy Search for Parameterized Skills using Adverbs作者 | Benjamin A. Spiegel, George Konidaris链接 | arxiv.org/abs/2110.1579 备注 | 7 pages, 3 figures

[52] On the Feasibility of Predicting Questions being Forgotten in Stack Overflow作者 | Thi Huyen Nguyen, Tu Nguyen, Tuan-Anh Hoang, Claudia Niederée链接 | arxiv.org/abs/2110.1578

[53] Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems作者 | Mohd Abbas Zaidi, Beomseok Lee, Nikhil Kumar Lakumarapu, Sangha Kim, Chanwoo Kim链接 | arxiv.org/abs/2110.1572 备注 | 5 pages, 3 figures, 1 table

[54] Fusing ASR Outputs in Joint Training for Speech Emotion Recognition作者 | Yuanchao Li, Peter Bell, Catherine Lai链接 | arxiv.org/abs/2110.1568 备注 | Submitted to ICASSP 2022

[55] Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction作者 | Heming Wang, Yao Qian, Xiaofei Wang, Yiming Wang, Chengyi Wang, Shujie Liu, Takuya Yoshioka, Jinyu Li, DeLiang Wang链接 | arxiv.org/abs/2110.1543 备注 | 5 pages, 1 figure, submitted to ICASSP 2022

[56] RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification作者 | Ajay Jaiswal, Liyan Tang, Meheli Ghosh, Justin Rousseau, Yifan Peng, Ying Ding链接 | arxiv.org/abs/2110.1542

[57] A Survey on Extraction of Causal Relations from Natural Language Text作者 | Jie Yang, Soyeon Caren Han, Josiah Poon链接 | arxiv.org/abs/2101.0642



机器学习/深度学习算法/自然语言处理交流群

已建立机器学习算法-自然语言处理微信交流群!想要进交流群进行学习的同学,可以直接加我的微信号:HIT_NLP。加的时候备注一下:知乎+学校+昵称 (不加备注不会接受同意,望谅解),想进pytorch群,备注知乎+学校+昵称+Pytorch即可。然后我们就可以拉你进群了。群里已经有非得多国内外高校同学,交流氛围非常好。

强烈推荐大家关注机器学习算法与自然语言处理账号和机器学习算法与自然语言处理微信公众号,可以快速了解到最新优质的干货资源。

推荐阅读

每日论文速递:计算机视觉相关(11月1日更新版) - 知乎 (zhihu.com)

北大万小军:如何应对科研中的困难与挑战 - 知乎 (zhihu.com)

实习招聘 | 微软亚洲研究院招聘talking face synthesis方向研究实习生 - 知乎 (zhihu.com)

实习招聘 | 创新工场首席科学家、原ACL主席、MSRA副院长周明老师招聘实习生 - 知乎 (zhihu.com)

IBM Watson「败走中国」内幕:认知推理远未成熟,却言必AI - 知乎 (zhihu.com)

60亿击败1750亿、验证胜过微调:OpenAI发现GPT-3解决数学题,并非参数越大越好 - 知乎 (zhihu.com)

Jeff Dean亲自揭秘谷歌下一代AI架构:通用、稀疏且高效,网友不买帐:毫无新意 - 知乎 (zhihu.com)

EMNLP 2021奖项公布,剑桥刘方宇、哥大杨子小帆一作论文分获最佳长、短论文奖 - 知乎 (zhihu.com)

NeurIPS 2021有哪些值得读的NLP论文? - 知乎 (zhihu.com)

图神经网络:Graph Neural Networks - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(10月29日更新版) - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(10月29日更新版) - 知乎 (zhihu.com)

2022 AI趋势8大预测 - 知乎 (zhihu.com)

招聘 | 百度搜索策略部招聘机器学习/数据挖掘/NLP/视觉算法工程师 - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(10月28日更新版) - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(10月28日更新版) - 知乎 (zhihu.com)

哈工大车万翔:如何做一个精彩的学术报告 - 知乎 (zhihu.com)

清华大学霸榜计算机学科第一!2022 USNews世界大学排名出炉,计算机前50中国占19个 - 知乎 (zhihu.com)

每日论文速递:自然语言处理相关(10月27日更新版) - 知乎 (zhihu.com)

每日论文速递:计算机视觉相关(10月27日更新版) - 知乎 (zhihu.com)

“大神”李沐造福社区 - 知乎 (zhihu.com)

Transformer在CV!前进,前进,前进进! - 知乎 (zhihu.com)

无敌!模型自动编写表格公式 - 知乎 (zhihu.com)

CCIR2021延期通知 - 知乎 (zhihu.com)

13个你一定要知道的PyTorch特性 - 知乎 (zhihu.com)

火爆全网,却只有4页!ICLR爆款论文「你只需要Patch」到底香不香? - 知乎 (zhihu.com)

博士论文写不好?Barrett博士发超强攻略,手把手教你写论文 - 知乎 (zhihu.com)

ICLR 2022哪篇论文最火?这个「集邮」狂魔放出3400篇大礼包 - 知乎 (zhihu.com)

编辑于 2021-11-01 22:55