每日论文速递:自然语言处理相关(5月19日更新版)
出品 | 深度学习这件小事公众号
如需转载,请联系后台授权
自然语言处理(5月19日更新版)
[1] Reconstructing Maps from Text
作者 | Johnathan E. Avery, Robert L. Goldstone, Michael N. Jones
链接 | https://arxiv.org/abs/2005.08932
[2] Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations
作者 | Sam Coope, Tyler Farghly, Daniela Gerz, Ivan Vulić, Matthew Henderson
链接 | https://arxiv.org/abs/2005.08866
备注 | ACL 2020
[3] Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings
作者 | Katherine McCurdy, Oguz Serbetci
链接 | https://arxiv.org/abs/2005.08864
备注 | Extended abstract presented at the WiNLP workshop, ACL 2017
[4] Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals
作者 | Kate McCurdy, Sharon Goldwater, Adam Lopez
链接 | https://arxiv.org/abs/2005.08826
备注 | To appear at ACL 2020
[5] Interaction Matching for Long-Tail Multi-Label Classification
作者 | Sean MacAvaney, Franck Dernoncourt, Walter Chang, Nazli Goharian, Ophir Frieder
链接 | https://arxiv.org/abs/2005.08805
[6] Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia
作者 | Sergey Zinin, Yang Xu
链接 | https://arxiv.org/abs/2005.08793
备注 | 12th Conference on Language Resources and Evaluation (LREC 2020)
[7] Improving Named Entity Recognition in Tor Darknet with Local Distance Neighbor Feature
作者 | Mhd Wesam Al-Nabki, Francisco Jañez-Martino, Roberto A. Vasco-Carofilis, Eduardo Fidalgo, Javier Velasco-Mata
链接 | https://arxiv.org/abs/2005.08746
备注 | to be published in conference JNIC 2020
[8] The presence of occupational structure in online texts based on word embedding NLP models
作者 | Zoltán Kmetty, Julia Koltai, Tamás Rudas
链接 | https://arxiv.org/abs/2005.08612
备注 | Paper presented at IC2S2 2019 and RC28 summer meeting 2019 (Columbia University)
[9] Efficient Wait-k Models for Simultaneous Machine Translation
作者 | Maha Elbayad, Laurent Besacier, Jakob Verbeek
链接 | https://arxiv.org/abs/2005.08595
[10] SemEval-2020 Task 5: Detecting Counterfactuals by Disambiguation
作者 | Hanna Abi Akl, Dominique Mariko, Estelle Labidurie
链接 | https://arxiv.org/abs/2005.08519
[11] Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks
作者 | Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Chitta Baral
链接 | https://arxiv.org/abs/2005.08516
[12] Text Classification with Few Examples using Controlled Generalization
作者 | Abhijit Mahabal, Jason Baldridge, Burcu Karagol Ayan, Vincent Perot, Dan Roth
链接 | https://arxiv.org/abs/2005.08469
[13] Syntax-guided Controlled Generation of Paraphrases
作者 | Ashutosh Kumar, Kabir Ahuja, Raghuram Vadapalli, Partha Talukdar
链接 | https://arxiv.org/abs/2005.08417
备注 | Accepted to TACL 2020
[14] MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform
作者 | Xiang Gao, Michel Galley, Bill Dolan
链接 | https://arxiv.org/abs/2005.08365
备注 | accepted at ACL 2020
[15] Cross-Lingual Word Embeddings for Turkic Languages
作者 | Elmurod Kuriyozov, Yerai Doval, Carlos Gómez-Rodríguez
链接 | https://arxiv.org/abs/2005.08340
备注 | Final version, published in the proceedings of LREC 2020
[16] Context-Based Quotation Recommendation
作者 | Ansel MacLaughlin, Tao Chen, Burcu Karagol Ayan, Dan Roth
链接 | https://arxiv.org/abs/2005.08319
[17] TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
作者 | Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel
链接 | https://arxiv.org/abs/2005.08314
备注 | To Appear at ACL 2020
[18] Support-BERT: Predicting Quality of Question-Answer Pairs in MSDN using Deep Bidirectional Transformer
作者 | Bhaskar Sen, Nikhil Gopal, Xinwei Xue
链接 | https://arxiv.org/abs/2005.08294
[19] LiSSS: A toy corpus of Literary Spanish Sentences Sentiment for Emotions Detection
作者 | Juan-Manuel Torres-Moreno, Luis-Gil Moreno-Jiménez
链接 | https://arxiv.org/abs/2005.08223
[20] Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation
作者 | Won Ik Cho, Donghyun Kwak, Jiwon Yoon, Nam Soo Kim
链接 | https://arxiv.org/abs/2005.08213
[21] Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles
作者 | Ben Eyal, Michael Elhadad
链接 | https://arxiv.org/abs/2005.08206
备注 | accepted to LREC 2020
[22] How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?
作者 | Gantavya Bhatt, Hritik Bansal, Rishubh Singh, Sumeet Agarwal
链接 | https://arxiv.org/abs/2005.08199
备注 | to appear at ACL SRW 2020
[23] Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
作者 | Juntao Li, Chang Liu, Jian Wang, Lidong Bing, Hongsong Li, Xiaozhong Liu, Dongyan Zhao, Rui Yan
链接 | https://arxiv.org/abs/2005.08188
备注 | AAAI 2020
[24] Multi-modal Automated Speech Scoring using Attention Fusion
作者 | Manraj Singh Grover, Yaman Kumar, Sumit Sarin, Payman Vafaee, Mika Hama, Rajiv Ratn Shah
链接 | https://arxiv.org/abs/2005.08182
备注 | Submitted to INTERSPEECH 2020
[25] IMoJIE: Iterative Memory-Based Joint Open Information Extraction
作者 | Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, Soumen Chakrabarti
链接 | https://arxiv.org/abs/2005.08178
[26] Encodings of Source Syntax: Similarities in NMT Representations Across Target Languages
作者 | Tyler A. Chang, Anna N. Rafferty
链接 | https://arxiv.org/abs/2005.08177
备注 | To appear at the 5th Workshop on Representation Learning for NLP
[27] Adversarial Training for Commonsense Inference
作者 | Lis Pereira, Xiaodong Liu, Fei Cheng, Masayuki Asahara, Ichiro Kobayashi
链接 | https://arxiv.org/abs/2005.08156
备注 | Accepted to ACL2020 RepL4NLP workshop
[28] Semi-Automating Knowledge Base Construction for Cancer Genetics
作者 | Somin Wadhwa, Kanhua Yin, Kevin S. Hughes, Byron C. Wallace
链接 | https://arxiv.org/abs/2005.08146
备注 | In proceedings of Automated Knowledge Base Construction (AKBC), 2020
[29] RPD: A Distance Function Between Word Embeddings
作者 | Xuhui Zhou, Zaixiang Zheng, Shujian Huang
链接 | https://arxiv.org/abs/2005.08113
备注 | ACL Student Research Workshop 2020
[30] Learning Probabilistic Sentence Representations from Paraphrases
作者 | Mingda Chen, Kevin Gimpel
链接 | https://arxiv.org/abs/2005.08105
备注 | Repl4NLP at ACL 2020, short paper
[31] Layer-Wise Cross-View Decoding for Sequence-to-Sequence Learning
作者 | Fenglin Liu, Xuancheng Ren, Guangxiang Zhao, Xu Sun
链接 | https://arxiv.org/abs/2005.08081
备注 | Achieve state-of-the-art BLEU scores on WMT14 EN-DE, EN-FR, and IWSLT DE-EN datasets
[32] Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehensio
作者 | Hongyu Gong, Yelong Shen, Dian Yu, Jianshu Chen, Dong Yu
链接 | https://arxiv.org/abs/2005.08056
[33] IntelliCode Compose: Code Generation Using Transformer
作者 | Alexey Svyatkovskiy, Shao Kun Deng, Shengyu Fu, Neel Sundaresan
链接 | https://arxiv.org/abs/2005.08025
[34] A Text Reassembling Approach to NaturalLanguage Generation
作者 | Xiao Li, Kees van Deemter, Chenghua Lin
链接 | https://arxiv.org/abs/2005.07988
[35] Unsupervised Embedding-based Detection of Lexical Semantic Changes
作者 | Ehsaneddin Asgari, Christoph Ringlstetter, Hinrich Schütze
链接 | https://arxiv.org/abs/2005.07979
[36] Logical Inferences with Comparatives and Generalized Quantifiers
作者 | Izumi Haruta, Koji Mineshima, Daisuke Bekki
链接 | https://arxiv.org/abs/2005.07954
备注 | To appear in the Proceedings of the Association for Computational Linguistics: Student Research Workshop (ACL-SRW 2020)
[37] ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them
作者 | Dawid Jurkiewicz, Łukasz Borchmann, Izabela Kosmala, Filip Graliński
链接 | https://arxiv.org/abs/2005.07934
[38] Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
作者 | Chao Xiong, Che Liu, Zijun Xu, Junfeng Jiang, Jieping Ye
链接 | https://arxiv.org/abs/2005.07923
[39] Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection
作者 | Lei Zhong, Juan Cao, Qiang Sheng, Junbo Guo, Ziang Wang
链接 | https://arxiv.org/abs/2005.07886
备注 | To appear in ACL 2020 (long paper)
[40] MicroNet for Efficient Language Modeling
作者 | Zhongxia Yan, Hanrui Wang, Demi Guo, Song Han
链接 | https://arxiv.org/abs/2005.07877
备注 | Accepted by PMLR
[41] Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms
作者 | Gale Yan Huang, Jiahao Chen, Haochen Liu, Weiping Fu, Wenbiao Ding, Jiliang Tang, Songfan Yang, Guoliang Li, Zitao Liu
链接 | https://arxiv.org/abs/2005.07845
备注 | The 21th International Conference on Artificial Intelligence in Education(AIED), 2020
[42] [email protected] at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT
作者 | Saja Khaled Tawalbeh, Mahmoud Hammad, Mohammad AL-Smadi
链接 | https://arxiv.org/abs/2005.07820
备注 | SemEval 2020 conference
[43] A Scientific Information Extraction Dataset for Nature Inspired Engineering
作者 | Ruben Kruiper, Julian F.V. Vincent, Jessica Chen-Burger, Marc P.Y. Desmulliez, Ioannis Konstas
链接 | https://arxiv.org/abs/2005.07753
备注 | Published in Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)
[44] In Layman's Terms: Semi-Open Relation Extraction from Scientific Texts
作者 | Ruben Kruiper, Julian F.V. Vincent, Jessica Chen-Burger, Marc P.Y. Desmulliez, Ioannis Konstas
链接 | https://arxiv.org/abs/2005.07751
备注 | To be published in ACL 2020 conference proceedings
[45] Uncovering Gender Bias in Media Coverage of Politicians with Machine Learning
作者 | Susan Leavy
链接 | https://arxiv.org/abs/2005.07734
备注 | Digital Scholarship in Humanities Journal
[46] Critical Impact of Social Networks Infodemic on Defeating Coronavirus COVID-19 Pandemic: Twitter-Based Study and Research Directions
作者 | Azzam Mourad, Ali Srour, Haidar Harmanani, Cathia Jenainatiy, Mohamad Arafeh
链接 | https://arxiv.org/abs/2005.08820
备注 | 11 pages, 10 figures, Journal Article
[47] Machine learning on Big Data from Twitter to understand public reactions to COVID-19
作者 | Jia Xue, Junxiang Chen, Chen Chen, ChengDa Zheng, Tingshao Zhu
链接 | https://arxiv.org/abs/2005.08817
[48] Conversational Search -- A Report from Dagstuhl Seminar 19461
作者 | Avishek Anand, Lawrence Cavedon, Matthias Hagen, Hideo Joho, Mark Sanderson, Benno Stein
链接 | https://arxiv.org/abs/2005.08658
备注 | contains arXiv:2001.06910, arXiv:2001.02912
[49] Design Choices for X-vector Based Speaker Anonymization
作者 | Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Junichi Yamagishi, Mohamed Maouche, Aurélien Bellet, Marc Tommasi
链接 | https://arxiv.org/abs/2005.08601
[50] Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation
作者 | Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Shang-Wen Li, Hung-yi Lee
链接 | https://arxiv.org/abs/2005.08575
[51] Audio-visual Multi-channel Recognition of Overlapped Speech
作者 | Jianwei Yu, Bo Wu, Rongzhi Gu Shi-Xiong Zhang Lianwu Chen Yong Xu Meng Yu, Dan Su, Dong Yu, Xunying Liu, Helen Meng
链接 | https://arxiv.org/abs/2005.08571
备注 | submitted to Interspeech 2020
[52] Robust Training of Vector Quantized Bottleneck Models
作者 | Adrian Łańcucki, Jan Chorowski, Guillaume Sanchez, Ricard Marxer, Nanxin Chen, Hans J.G.A. Dolfing, Sameer Khurana, Tanel Alumäe, Antoine Laurent
链接 | https://arxiv.org/abs/2005.08520
备注 | Published at IJCNN 2020
[53] Attention-based Transducer for Online Speech Recognition
作者 | Bin Wang, Yan Yin, Hui Lin
链接 | https://arxiv.org/abs/2005.08497
备注 | submitted to Interspeech 2020
[54] An Effective End-to-End Modeling Approach for Mispronunciation Detection
作者 | Tien-Hong Lo, Shi-Yan Weng, Hsiu-Jui Chang, Berlin Chen
链接 | https://arxiv.org/abs/2005.08440
备注 | Submitted to Interspeech 2020
[55] The NTNU System at the Interspeech 2020 Non-Native Children's Speech ASR Challenge
作者 | Tien-Hong Lo, Fu-An Chao, Shi-Yan Weng, Berlin Chen
链接 | https://arxiv.org/abs/2005.08433
备注 | Submitted to Interspeech 2020 Special Session: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech
[56] Content analysis of Persian/Farsi Tweets during COVID-19 pandemic in Iran using NLP
作者 | Pedram Hosseini, Poorya Hosseini, David A. Broniatowski
链接 | https://arxiv.org/abs/2005.08400
[57] Vector-Quantized Autoregressive Predictive Coding
作者 | Yu-An Chung, Hao Tang, James Glass
链接 | https://arxiv.org/abs/2005.08392
[58] Fixed Point Semantics for Stream Reasoning
作者 | Christian Antić
链接 | https://arxiv.org/abs/2005.08384
[59] Wake Word Detection with Alignment-Free Lattice-Free MMI
作者 | Yiming Wang, Hang Lv, Daniel Povey, Lei Xie, Sanjeev Khudanpur
链接 | https://arxiv.org/abs/2005.08347
备注 | Submitted to INTERSPEECH 2020
[60] A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
作者 | Vladimir Iashin, Esa Rahtu
链接 | https://arxiv.org/abs/2005.08271
项目链接 | https://v-iashin.github.io/bmt
[61] On the Combined Use of Extrinsic Semantic Resources for Medical Information Search
作者 | Mohammed Maree, Israa Noor, Khaled Rabayah, Mohammed Belkhatir, Saadat M. Alhashmi
链接 | https://arxiv.org/abs/2005.08259
[62] Dual Learning: Theoretical Study and an Algorithmic Extension
作者 | Zhibing Zhao, Yingce Xia, Tao Qin, Lirong Xia, Tie-Yan Liu
链接 | https://arxiv.org/abs/2005.08238
[63] #Coronavirus or #Chinesevirus?!: Understanding the negative sentiment reflected in Tweets with racist hashtags across the development of COVID-19
作者 | Xin Pei, Deval Mehta
链接 | https://arxiv.org/abs/2005.08224
[64] That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
作者 | Piotr Żelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
链接 | https://arxiv.org/abs/2005.08118
备注 | Submitted to Interspeech 2020. For some reason, the ArXiv Latex engine rendered it in more than 4 pages
[65] Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models
作者 | Qiang Huang, Thomas Hain
链接 | https://arxiv.org/abs/2005.08053
备注 | Submitted to InterSpeech 2020
[66] Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory
作者 | Chunyang Wu, Yongqiang Wang, Yangyang Shi, Ching-Feng Yeh, Frank Zhang
链接 | https://arxiv.org/abs/2005.08042
备注 | submitted to Interspeech 2020
[67] Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation
作者 | Tao Tu, Yuan-Jui Chen, Alexander H. Liu, Hung-yi Lee
链接 | https://arxiv.org/abs/2005.08024
备注 | Submitted to Interspeech 2020
[68] AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition
作者 | Afroz Ahamad, Ankit Anand, Pranesh Bhargava
链接 | https://arxiv.org/abs/2005.07973
备注 | Proceedings of the 12th Language Resources and Evaluation Conference - LREC, 2020
[69] Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss
作者 | Burin Naowarat, Thananchai Kongthaworn, Korrawe Karunratanakul, Sheng Hui Wu, Ekapol Chuangsuwanich
链接 | https://arxiv.org/abs/2005.07920
备注 | 7 pages, 5 figures, submitted to INTERSPEECH 2020
[70] Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition
作者 | Zhengkun Tian, Jiangyan Yi, Jianhua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen
链接 | https://arxiv.org/abs/2005.07903
[71] Oscillating Statistical Moments for Speech Polarity Detection
作者 | Thomas Drugman, Thierry Dutoit
链接 | https://arxiv.org/abs/2005.07901
[72] Glottal Source Estimation using an Automatic Chirp Decomposition
作者 | Thomas Drugman, Baris Bozkurt, Thierry Dutoit
链接 | https://arxiv.org/abs/2005.07897
[73] Large scale weakly and semi-supervised learning for low-resource video ASR
作者 | Kritika Singh, Vimal Manohar, Alex Xiao, Sergey Edunov, Ross Girshick, Vitaliy Liptchinsky, Christian Fuegen, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed
链接 | https://arxiv.org/abs/2005.07850
[74] Speaker Re-identification with Speaker Dependent Speech Enhancement
作者 | Yanpei Shi, Qiang Huang, Thomas Hain
链接 | https://arxiv.org/abs/2005.07818
备注 | Submitted to Interspeech2020
[75] Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
作者 | Yanpei Shi, Qiang Huang, Thomas Hain
链接 | https://arxiv.org/abs/2005.07817
备注 | Submitted to Interspeech2020
[76] Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions
作者 | Zhuohao Chen, Nikolaos Flemotomos, Victor Ardulov, Torrey A. Creed, Zac E. Imel, David C. Atkins, Shrikanth Narayanan
链接 | https://arxiv.org/abs/2005.07809
备注 | Submitted to Interspeech 2020
[77] JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment
作者 | Dan Lim, Won Jang, Gyeonghwan O, Hyeyeong Park, Bongwan Kim, Jesam Yoon
链接 | https://arxiv.org/abs/2005.07799
备注 | submitted to INTERSPEECH 2020
重磅!忆臻自然语言处理-学术微信交流群已成立
可以扫描下方二维码,小助手将会邀请您入群交流,
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:
百闻不如一码!手把手教你用Python搭一个Transformer