出品 | 深度学习这件小事公众号
自然语言处理（4月5日更新版）
[1] Exploring Transformers in Emotion Recognition: a comparison of BERT, DistillBERT, RoBERTa, XLNet and ELECTRA
链接 | https://arxiv.org/abs/2104.02041
[2] Intent detection and slot filling for Vietnamese
作者 | Mai Hoang Dao, Thinh Hung Truong, Dat Quoc Nguyen
链接 | https://arxiv.org/abs/2104.02021
[3] SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
作者 | Patrick K. O'Neill, Vitaly Lavrukhin, Somshubra Majumdar, Vahid Noroozi, Yuekai Zhang, Oleksii Kuchaiev, Jagadeesh Balam, Yuliya Dovzhenko, Keenan Freyberg, Michael D. Shulman, Boris Ginsburg, Shinji Watanabe, Georg Kucsko
链接 | https://arxiv.org/abs/2104.02014
备注 | 5 pages, 1 figure. Submitted to INTERSPEECH 2021
[4] Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition
作者 | Jason Pelecanos, Quan Wang, Ignacio Lopez Moreno
链接 | https://arxiv.org/abs/2104.01989
备注 | Submission to Interspeech 2021
[5] Automating Transfer Credit Assessment in Student Mobility -- A Natural Language Processing-based Approach
作者 | Dhivya Chandrasekaran, Vijay Mago
链接 | https://arxiv.org/abs/2104.01955
备注 | 13 pages and 5 figures
[6] What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult
作者 | Avishai Zagoury, Einat Minkov, Idan Szpektor, William W. Cohen
链接 | https://arxiv.org/abs/2104.01940
[7] Mining Customers' Opinions for Online Reputation Generation and Visualization in e-Commerce Platforms
作者 | Abdessamad Benlahbib
链接 | https://arxiv.org/abs/2104.01935
[8] Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval
作者 | Ramon Sanabria, Austin Waters, Jason Baldridge
链接 | https://arxiv.org/abs/2104.01894
备注 | Submitted to INTERSPEECH 2021
[9] Rethinking Perturbations in Encoder-Decoders for Fast Training
作者 | Sho Takase, Shun Kiyono
链接 | https://arxiv.org/abs/2104.01853
备注 | Accepted at NAACL-HLT 2021
[10] Deep Neural Networks for Relation Extraction
链接 | https://arxiv.org/abs/2104.01799
备注 | PhD Thesis, National University of Singapore (2020)
[11] A Heuristic-driven Uncertainty based Ensemble Framework for Fake News Detection in Tweets and News Articles
作者 | Sourya Dipta Das, Ayan Basak, Saikat Dutta
链接 | https://arxiv.org/abs/2104.01791
备注 | submitted to Neurocomputing. arXiv admin note: substantial text overlap with arXiv:2101.03545
[12] BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification
链接 | https://arxiv.org/abs/2104.01782
备注 | To appear in NAACL 2021
[13] WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach
作者 | Junjie Huang, Duyu Tang, Wanjun Zhong, Shuai Lu, Linjun Shou, Ming Gong, Daxin Jiang, Nan Duan
链接 | https://arxiv.org/abs/2104.01767
[14] Paired Examples as Indirect Supervision in Latent Decision Models
作者 | Nitish Gupta, Sameer Singh, Matt Gardner, Dan Roth
链接 | https://arxiv.org/abs/2104.01759
[15] A New Approach to Overgenerating and Scoring Abstractive Summaries
作者 | Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu
链接 | https://arxiv.org/abs/2104.01726
备注 | NAACL 2021 (Long Paper)
[16] Inference Time Style Control for Summarization
作者 | Shuyang Cao, Lu Wang
链接 | https://arxiv.org/abs/2104.01724
备注 | Accepted at NAACL 2021 (short paper)
[17] FixMyPose: Pose Correctional Captioning and Retrieval
作者 | Hyounghun Kim, Abhay Zala, Graham Burri, Mohit Bansal
链接 | https://arxiv.org/abs/2104.01703
[18] A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
作者 | Tuan Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, Walter Chang
链接 | https://arxiv.org/abs/2104.01697
备注 | Accepted by NAACL 2021
[19] Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
作者 | Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu
链接 | https://arxiv.org/abs/2104.01666
备注 | Accepted to Main Conference of NAACL 2021 as Long Paper
[20] Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
作者 | Kathleen Siminyu, Xinjian Li, Antonios Anastasopoulos, David Mortensen, Michael R. Marlo, Graham Neubig
链接 | https://arxiv.org/abs/2104.01624
[21] KnowGraph@IITK at SemEval-2021 Task 11: Building KnowledgeGraph for NLP Research
作者 | Shashank Shailabh, Sajal Chaurasia, Ashutosh Modi
链接 | https://arxiv.org/abs/2104.01619
备注 | Accepted at SemEval 2021 Task 11, 11 Pages (9 Pages main content+ 2 pages for references)
[22] Towards Lifelong Learning of End-to-end ASR
作者 | Heng-Jui Chang, Hung-yi Lee, Lin-shan Lee
链接 | https://arxiv.org/abs/2104.01616
备注 | Submitted to INTERSPEECH 2021
[23] Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
作者 | Loren Lugosch, Piyush Papreja, Mirco Ravanelli, Abdelwahab Heba, Titouan Parcollet
链接 | https://arxiv.org/abs/2104.01604
[24] TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling
作者 | Tze Yuang Chong, Xuyang Wang, Lin Yang, Junjie Wang
链接 | https://arxiv.org/abs/2104.01572
备注 | INTERSPEECH 2021 (under reviewed)
[25] Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks
作者 | Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova
链接 | https://arxiv.org/abs/2104.01569
备注 | 16th conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)
[26] MCL@IITK at SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation using Augmented Data, Signals, and Transformers
作者 | Rohan Gupta, Jay Mundra, Deepak Mahajan, Ashutosh Modi
链接 | https://arxiv.org/abs/2104.01567
备注 | Accepted at SemEval 2021 Task 2, 10 Pages (8 Pages main content+ 2 pages for references)
[27] IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection
作者 | Archit Bansal, Abhay Kaushik, Ashutosh Modi
链接 | https://arxiv.org/abs/2104.01566
备注 | Accepted at SemEval 2021 Task 5, 9 Pages (6 Pages main content + 1 Page for references + 2 Pages Appendix)
[28] ReCAM@IITK at SemEval-2021 Task 4: BERT and ALBERT based Ensemble for Abstract Word Prediction
作者 | Abhishek Mittal, Ashutosh Modi
链接 | https://arxiv.org/abs/2104.01563
备注 | Accepted at SemEval 2021 Task 4, 8 Pages (7 Pages main content + 1 pages for references)
[29] A Conversational Agent System for Dietary Supplements Use
作者 | Esha Singh, Anu Bompelli, Ruyuan Wan, Jiang Bian, Serguei Pakhomov, Rui Zhang
链接 | https://arxiv.org/abs/2104.01543
[30] ASPER: Attention-based Approach to Extract Syntactic Patterns denoting Semantic Relations in Sentential Context
作者 | Md. Ahsanul Kabir, Typer Phillips, Xiao Luo, Mohammad Al Hasan
链接 | https://arxiv.org/abs/2104.01523
[31] Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
作者 | Hosein Mohebbi, Ali Modarressi, Mohammad Taher Pilehvar
链接 | https://arxiv.org/abs/2104.01477
[32] Few-Shot Keyword Spotting in Any Language
作者 | Mark Mazumder, Colby Banbury, Josh Meyer, Pete Warden, Vijay Janapa Reddi
链接 | https://arxiv.org/abs/2104.01454
[33] Sexism detection: The first corpus in Algerian dialect with a code-switching in Arabic/ French and English
作者 | Imane Guellil, Ahsan Adeel, Faical Azouaou, Mohamed Boubred, Yousra Houichi, Akram Abdelhaq Moumna
链接 | https://arxiv.org/abs/2104.01443
备注 | This paper was accepted at the AfricanNLP workshop (EACL conference 2021)
[34] Unsupervised Domain Adaptation with Global and Local Graph Neural Networks in Limited Labeled Data Scenario: Application to Disaster Management
作者 | Samujjwal Ghosh, Subhadeep Maji, Maunendra Sankar Desarkar
链接 | https://arxiv.org/abs/2104.01436
备注 | This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
[35] Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
作者 | Rui Liu, Berrak Sisman, Haizhou Li
链接 | https://arxiv.org/abs/2104.01408
备注 | 5 pages, 4 figures, Submitted to Interspeech 2021
[36] On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR
作者 | Tsz Kin Lam, Mayumi Ohta, Shigehiko Schamoni, Stefan Riezler
链接 | https://arxiv.org/abs/2104.01393
备注 | Submitted to INTERSPEECH 2021
[37] speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment
作者 | Junbo Zhang, Zhiwen Zhang, Yongqing Wang, Zhiyong Yan, Qiong Song, Yukai Huang, Ke Li, Daniel Povey, Yujun Wang
链接 | https://arxiv.org/abs/2104.01378
[38] Convex Aggregation for Opinion Summarization
作者 | Hayate Iso, Xiaolan Wang, Yoshihiko Suhara, Stefanos Angelidis, Wang-Chiew Tan
链接 | https://arxiv.org/abs/2104.01371
[39] Counts@IITK at SemEval-2021 Task 8: SciBERT Based Entity And Semantic Relation Extraction For Scientific Data
作者 | Akash Gangwar, Sabhay Jain, Shubham Sourav, Ashutosh Modi
链接 | https://arxiv.org/abs/2104.01364
备注 | Accepted at SemEval 2021 Task 8, 7 Pages (5 Pages main content + 1 page for references + 1 Page Appendix)
[40] From n-grams to trees in Lindenmayer systems
作者 | Diego Gabriel Krivochen
链接 | https://arxiv.org/abs/2104.01363
[41] Global Syntactic Variation in Seven Languages: Towards a Computational Dialectology
链接 | https://arxiv.org/abs/2104.01306
[42] Finding Variants for Construction-Based Dialectometry: A Corpus-Based Approach to Regional CxGs
链接 | https://arxiv.org/abs/2104.01299
[43] Multi-Unit Directional Measures of Association: Moving Beyond Pairs of Words
链接 | https://arxiv.org/abs/2104.01297
[44] Representations of Language Varieties Are Reliable Given Corpus Similarity Measures
链接 | https://arxiv.org/abs/2104.01294
[45] Measuring Linguistic Diversity During COVID-19
作者 | Jonathan Dunn, Tom Coupe, Benjamin Adams
链接 | https://arxiv.org/abs/2104.01290
[46] Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems
作者 | Akshat Gupta, Sai Krishna Rallabandi, Alan W Black
链接 | https://arxiv.org/abs/2104.01287
[47] Attention Forcing for Machine Translation
作者 | Qingyun Dou, Yiting Lu, Potsawee Manakul, Xixin Wu, Mark J. F. Gales
链接 | https://arxiv.org/abs/2104.01264
备注 | arXiv admin note: text overlap with arXiv:1909.12289
[48] Type Prediction Systems
作者 | Sarthak Dash, Nandana Mihindukulasooriya, Alfio Gliozzo, Mustafa Canim
链接 | https://arxiv.org/abs/2104.01207
[49] StarGAN-based Emotional Voice Conversion for Japanese Phrases
作者 | Asuka Moritani, Ryo Ozaki, Shoki Sakamoto, Hirokazu Kameoka, Tadahiro Taniguchi
链接 | https://arxiv.org/abs/2104.01807
备注 | Submitted to Interspeech 2021
[50] Annotating Columns with Pre-trained Language Models
作者 | Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan
链接 | https://arxiv.org/abs/2104.01785
[51] Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models
作者 | Martin Weyssow, Houari Sahraoui, Eugene Syriani
链接 | https://arxiv.org/abs/2104.01642
[52] Perspective-corrected Spatial Referring Expression Generation for Human-Robot Interaction
作者 | Mingjiang Liu, Chengli Xiao, Chunlin Chen
链接 | https://arxiv.org/abs/2104.01558
备注 | Under review, 20 pages, 12 figures
[53] TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition
作者 | Zhengkun Tian, Jiangyan Yi, Jianhua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen, Xuefei Liu
链接 | https://arxiv.org/abs/2104.01522
备注 | Submitted to Interspeech2021
[54] Medical Entity Disambiguation Using Graph Neural Networks
作者 | Alina Vretinaris, Chuan Lei, Vasilis Efthymiou, Xiao Qin, Fatma Özcan
链接 | https://arxiv.org/abs/2104.01488
备注 | To appear in SIGMOD 2021
[55] MMBERT: Multimodal BERT Pretraining for Improved Medical VQA
作者 | Yash Khare, Viraj Bagal, Minesh Mathew, Adithi Devi, U Deva Priyakumar, CV Jawahar
链接 | https://arxiv.org/abs/2104.01394
[56] ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of Kaldi
作者 | Yu Wang, Chee Siang Leow, Akio Kobayashi, Takehito Utsuro, Hiromitsu Nishizaki
链接 | https://arxiv.org/abs/2104.01384
备注 | Submitted to INTERSPEECH2021
[57] Fingerspelling Detection in American Sign Language
作者 | Bowen Shi, Diane Brentari, Greg Shakhnarovich, Karen Livescu
链接 | https://arxiv.org/abs/2104.01291
[58] The Coronavirus is a Bioweapon: Analysing Coronavirus Fact-Checked Stories
作者 | Lynnette Hui Xian Ng, Kathleen M. Carley
链接 | https://arxiv.org/abs/2104.01215
点击下方卡片，关注公众号“机器学习算法与自然语言处理”，获取更多信息：
下载1：四件套
在机器学习算法与自然语言处理公众号后台回复“四件套”，
即可获取学习TensorFlow，Pytorch，机器学习，深度学习四件套！
下载2：仓库地址共享
在机器学习算法与自然语言处理公众号后台回复“代码”，
即可获取195篇NAACL+295篇ACL2019有代码开源的论文。开源地址如下：https://github.com/yizhen20133868/NLP-Conferences-Code
重磅！机器学习算法与自然语言处理交流群已正式成立！
群内有大量资源，欢迎大家进群学习！
额外赠送福利资源！深度学习与神经网络，pytorch官方中文教程，利用Python进行数据分析，机器学习学习笔记，pandas官方文档中文版，effective java（中文版）等20项福利资源
获取方式：进入群后点开群公告即可领取下载链接
注意：请大家添加时修改备注为 [学校/公司 + 姓名 + 方向]
例如 —— 哈工大+张三+对话系统。
号主，微商请自觉绕道。谢谢！
推荐阅读：
Transformer升级之路：博采众长的旋转式位置编码
抽取式摘要最新研究进展
「新生手册」：PyTorch分布式训练
点击下方卡片，关注公众号“机器学习算法与自然语言处理”，获取更多信息：
