《一週新論文》系列之2020年第10周：自然語言處理相關
本週重點關注：
- Microsoft: [29], [32], [43], [59], [63]
- Amazon: [14]
- Google: [5], [13]
- 其他: [18], [31], [33], [34], [35], [40], [45], [47], [50]
2020年3月6日
[1]. An Empirical Accuracy Law for Sequential Machine Translation: the Case of Google Translate
鏈接 | https://arxiv.org/abs/2003.02817
作者 | Lucas Nunes Sequeira, Bruno Moreschi, Fabio Gagliardi Cozman, Bernardo Fontes
[2]. HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference
鏈接 | https://arxiv.org/abs/2003.02756
作者 | Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui
單位 | Peking University; Peng Cheng Laboratory; Beijing University of Posts and Telecommunications
備註 | LREC 2020
[3]. Zero-Shot Cross-Lingual Transfer with Meta Learning
鏈接 | https://arxiv.org/abs/2003.02739
作者 | Farhad Nooralahzadeh, Giannis Bekoulis, Johannes Bjerva, Isabelle Augenstein
[4]. Fact Check-Worthiness Detection as Positive Unlabelled Learning
鏈接 | https://arxiv.org/abs/2003.02736
作者 | Dustin Wright, Isabelle Augenstein
[5]. SentenceMIM: A Latent Variable Language Model
鏈接 | https://arxiv.org/abs/2003.02645
作者 | Micha Livne, Kevin Swersky, David J. Fleet
單位 | University of Toronto; Vector Institute; Google Research, Toronto
[6]. RecipeGPT: Generative Pre-training Based Cooking Recipe Generation and Evaluation System
鏈接 | https://arxiv.org/abs/2003.02498
作者 | Helena H. Lee, Ke Shu, Palakorn Achananuparp, Philips Kokoh Prasetyo, Yue Liu, Ee-Peng Lim, Lav R. Varshney
單位 | Singapore Management University; University of Illinois at Urbana-Champaign
[7]. Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout
鏈接 | https://arxiv.org/abs/2003.02356
作者 | Filip Graliński, Tomasz Stanisławek, Anna Wróblewska, Dawid Lipiński, Agnieszka Kaliska, Paulina Rosalska, Bartosz Topolski, Przemysław Biecek
[8]. A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection
鏈接 | https://arxiv.org/abs/2003.02349
作者 | Daniele Bonadiman, Alessandro Moschitti
單位 | Amazon Alexa
[9]. BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward
鏈接 | https://arxiv.org/abs/2003.02738
作者 | Florian Schmidt, Thomas Hofmann
[10]. Phase transitions in a decentralized graph-based approach to human language
鏈接 | https://arxiv.org/abs/2003.02639
作者 | Javier Vera, Felipe Urbina, Wenceslao Palma
[11]. An Incremental Explanation of Inference in Hybrid Bayesian Networks for Increasing Model Trustworthiness and Supporting Clinical Decision Making
鏈接 | https://arxiv.org/abs/2003.02599
作者 | Evangelia Kyrimi, Somayyeh Mossadegh, Nigel Tai, William Marsh
[12]. Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
鏈接 | https://arxiv.org/abs/2003.02301
作者 | Yi Xie, Cong Shi, Zhuohang Li, Jian Liu, Yingying Chen, Bo Yuan
單位 | Rutgers University;
2020年3月5日
[13]. jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
鏈接 | https://arxiv.org/abs/2003.02249
作者 | Yada Pruksachatkun, Phil Yeres, Haokun Liu, Jason Phang, Phu Mon Htut, Alex Wang, Ian Tenney, Samuel R. Bowman
單位 | New York University; Google Research
[14]. Data Augmentation using Pre-trained Transformer Models
鏈接 | https://arxiv.org/abs/2003.02245
作者 | Varun Kumar, Ashutosh Choudhary, Eunah Cho
單位 | Amazon
[15]. Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification
鏈接 | https://arxiv.org/abs/2003.02244
作者 | Hsin-Ping Huang, Junyi Jessy Li
單位 | The University of Texas at Austin
備註 | CoNLL 2019
[16]. Evaluating Low-Resource Machine Translation between Chinese and Vietnamese with Back-Translation
鏈接 | https://arxiv.org/abs/2003.02197
作者 | Hongzheng Li, Heyan Huang
單位 | Beijing Institute of Technology
[17]. Sequential Neural Networks for Noetic End-to-End Response Selection
鏈接 | https://arxiv.org/abs/2003.02126
作者 | Qian Chen, Wen Wang
單位 | Alibaba Group
[18]. Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network
鏈接 | https://arxiv.org/abs/2003.02020
作者 | Shaoxiong Feng, Hongshen Chen, Kan Li, Dawei Yin
單位 | Beijing Institute of Technology; JD.com
備註 | Accepted by AAAI 2020
[19]. Restoration of Fragmentary Babylonian Texts Using Recurrent Neural Networks
鏈接 | https://arxiv.org/abs/2003.01912
作者 | Ethan Fetaya, Yonatan Lifshitz, Elad Aaron, Shai Gordin
[20]. SeMemNN: A Semantic Matrix-Based Memory Neural Network for Text Classification
鏈接 | https://arxiv.org/abs/2003.01857
作者 | Changzeng Fu, Chaoran Liu, Carlos Toshinori Ishi, Yuichiro Yoshikawa, Hiroshi Ishiguro
[21]. HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statistics
鏈接 | https://arxiv.org/abs/2003.01821
作者 | Pedro Alonso, Kumar Shridhar, Denis Kleyko, Evgeny Osipov, Marcus Liwicki
[22]. AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
鏈接 | https://arxiv.org/abs/2003.01950
作者 | Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, Jing Xiao
單位 | Ping An Technology
備註 | will be presented in ICASSP 2020
[23]. GraphTTS: graph-to-sequence modelling in neural text-to-speech
鏈接 | https://arxiv.org/abs/2003.01950
作者 | Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng, Zhen Zeng, Jing Xiao
單位 | Ping An Technology
備註 | Accepted to ICASSP 2020
[24]. On Emergent Communication in Competitive Multi-Agent Teams
鏈接 | https://arxiv.org/abs/2003.01848
作者 | Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur
單位 | Carnegie Mellon University
備註 | AAMAS 2020
[25]. Discover Your Social Identity from What You Tweet: a Content Based Approach
鏈接 | https://arxiv.org/abs/2003.01797
作者 | Binxuan Huang, Kathleen M. Carley
單位 | Carnegie Mellon University
[26]. Untangling in Invariant Speech Recognition
鏈接 | https://arxiv.org/abs/2003.01787
作者 | Cory Stephenson, Jenelle Feather, Suchismita Padhy, Oguz Elibol, Hanlin Tang, Josh McDermott, SueYeon Chung
單位 | Intel AI Lab; MIT; Columbia University
備註 | Advances in Neural Information Processing Systems. 2019
[27]. Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data
鏈接 | https://arxiv.org/abs/2003.01769
作者 | Peter Plantinga, Deblin Bagchi, Eric Fosler-Lussier
單位 | The Ohio State University
備註 | 4 pages + 1 page for references, accepted to ICASSP 2020
[28]. Towards Real-time Mispronunciation Detection in Kids’ Speech
鏈接 | https://arxiv.org/abs/2003.01765
作者 | Peter Plantinga, Eric Fosler-Lussier
單位 | The Ohio State University
備註 | 6 pages + 1 page for references, accepted at ASRU 2019
2020年3月4日
[29]. Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation
鏈接 | https://arxiv.org/abs/2003.01680
作者 | Igor Shalyminov, Alessandro Sordoni, Adam Atkinson, Hannes Schulz
單位 | Microsoft Research
備註 | Presented at DSTC8@AAAI 2020
[30]. Improving Uyghur ASR systems with decoders using morpheme-based language models
鏈接 | https://arxiv.org/abs/2003.01509
作者 | Zicheng Qiu, Wei Jiang, Turghunjan Mamut
[31]. Multi-Task Learning Network for Emotion Recognition in Conversation
鏈接 | https://arxiv.org/abs/2003.01478
作者 | Jingye Li, Meishan Zhang, Donghong Ji, Yijiang Liu
單位 | Wuhan University; Tianjin University
[32]. XGPT: Cross-modal Generative Pre-Training for Image Captioning
鏈接 | https://arxiv.org/abs/2003.01473
作者 | Qiaolin Xia, Haoyang Huang, Nan Duan, Dongdong Zhang, Lei Ji, Zhifang Sui, Edward Cui, Taroon Bharti, Ming Zhou
單位 | Peking University; Microsoft Research Asia
[33]. Meta-Embeddings Based On Self-Attention
鏈接 | https://arxiv.org/abs/2003.01371
作者 | Qichen Li, Xiaoke Jiang, Jun Xia, Jian Li
單位 | SenseTime; Tsinghua University
[34]. CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model
鏈接 | https://arxiv.org/abs/2003.01355
作者 | Liang Xu, Xuanwei Zhang, Qianqian Dong
[35]. Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
鏈接 | https://arxiv.org/abs/2003.01343
作者 | Shuyan Zhou, Shruti Rijhawani, John Wieting, Jaime Carbonell, Graham Neubig
單位 | Carnegie Mellon University
備註 | Accepted to TACL 2020
[36]. Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection
鏈接 | https://arxiv.org/abs/2003.01309
作者 | Qian Chen, Mengzhe Chen, Bo Li, Wen Wang
單位 | Alibaba Group
備註 | 4 pages, 2 figures, accepted by ICASSP 2020
[37]. Transfer Learning for Context-Aware Spoken Language Understanding
鏈接 | https://arxiv.org/abs/2003.01305
作者 | Qian Chen, Zhu Zhuo, Wen Wang, Qiuyun Xu
單位 | Alibaba Group
備註 | 6 pages, 3 figures, ASRU2019
[38]. Med7: a transferable clinical natural language processing model for electronic health records
鏈接 | https://arxiv.org/abs/2003.01271
作者 | Andrey Kormilitzin, Nemanja Vaci, Qiang Liu, Alejo Nevado-Holgado
[39]. Understanding the Prediction Mechanism of Sentiments by XAI Visualization
鏈接 | https://arxiv.org/abs/2003.01425
作者 | Chaehan So
備註 | This is the author’s prefinal version be published in conference proceedings: 4th International Conference on Natural Language Processing and Information Retrieval, Sejong, South Korea, 26-28 June, 2020, ACM
[40]. Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion
鏈接 | https://arxiv.org/abs/2003.01338
作者 | Jingyuan Yang, Guang Liu, Yuzhao Mao, Zhiwei Zhao, Weiguo Gao, Xuan Li, Haiqin Yang, Jianping Shen
單位 | Ping An Technology
備註 | Presented at DSTC workshop, AAAI 2020
2020年3月3日
[41]. Gated Mechanism for Attention Based Multimodal Sentiment Analysis
鏈接 | https://arxiv.org/abs/2003.01043
作者 | Ayush Kumar, Jithendra Vepa
備註 | Accepted to appear in ICASSP 2020
[42]. Identification of primary and collateral tracks in stuttered speech
鏈接 | https://arxiv.org/abs/2003.01018
作者 | Rachid Riad, Anne-Catherine Bachoud-Lévi, Frank Rudzicz, Emmanuel Dupoux
備註 | To be published in LREC 2020
[43]. Multi-View Learning for Vision-and-Language Navigation
鏈接 | https://arxiv.org/abs/2003.00857
作者 | Qiaolin Xia, Xiujun Li, Chunyuan Li, Yonatan Bisk, Zhifang Sui, Yejin Choi, Noah A. Smith
單位 | University of Washington; Peking University; Microsoft Research;
[44]. PhoBERT: Pre-trained language models for Vietnamese
鏈接 | https://arxiv.org/abs/2003.00744
作者 | Dat Quoc Nguyen, Anh Tuan Nguyen
[45]. Style Example-Guided Text Generation using Generative Adversarial Transformers
鏈接 | https://arxiv.org/abs/2003.00674
作者 | Kuo-Hao Zeng, Mohammad Shoeybi, Ming-Yu Liu
單位 | NVIDIA
[46]. Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
鏈接 | https://arxiv.org/abs/2003.00639
作者 | Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Yangxi Li, Dongsheng Duan, Dawei Yin
單位 | Chinese Academy of Sciences
備註 | AAAI 2020
[47]. StructSum: Incorporating Latent and Explicit Sentence Dependencies for Single Document Summarization
鏈接 | https://arxiv.org/abs/2003.00576
作者 | Vidhisha Balachandran, Artidoro Pagnoni, Jay Yoon Lee, Dheeraj Rajagopal, Jaime Carbonell, Yulia Tsvetkov
單位 | Carnegie Mellon University
[48]. Clinical Text Summarization with Syntax-Based Negation and Semantic Concept Identification
鏈接 | https://arxiv.org/abs/2003.00353
作者 | Wei-Hung Weng, Yu-An Chung, Schrasing Tong
單位 | MIT
[49]. Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks
鏈接 | https://arxiv.org/abs/2003.00304
作者 | Woojay Jeon, Leo Liu, Henry Mason
單位 | Apple
備註 | Presented at IEEE ICASSP, May 2019
[50]. Depth-Adaptive Graph Recurrent Network for Text Classification
鏈接 | https://arxiv.org/abs/2003.00166
作者 | Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jie Zhou
單位 | Beijing Jiaotong University; Tencent
[51]. AraBERT: Transformer-based Model for Arabic Language Understanding
鏈接 | https://arxiv.org/abs/2003.00104
作者 | Wissam Antoun, Fady Baly, Hazem Hajj
[52]. The STEM-ECR Dataset: Grounding Scientific Entity References in STEM Scholarly Content to Authoritative Encyclopedic and Lexicographic Sources
鏈接 | https://arxiv.org/abs/2003.01006
作者 | Jennifer D’Souza, Anett Hoppe, Arthur Brack, Mohamad Yaser Jaradeh, Sören Auer, Ralph Ewerth
備註 | To appear in LREC 2020 proceedings. 11 pages, 6 figures
[53]. Pathological speech detection using x-vector embeddings
鏈接 | https://arxiv.org/abs/2003.00864
作者 | Catarina Botelho, Francisco Teixeira, Thomas Rolland, Alberto Abad, Isabel Trancoso
備註 | Submitted to EUSIPCO 2020
[54]. Long Short-Term Sample Distillation
鏈接 | https://arxiv.org/abs/2003.00739
作者 | Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi
單位 | Ant Financial Services Group; Rutgers University
備註 | published as a conference paper at AAAI 2020
[55]. Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
鏈接 | https://arxiv.org/abs/2003.00443
作者 | Xin Wang, Vihan Jain, Eugene Ie, William Yang Wang, Zornitsa Kozareva, Sujith Ravi
單位 | University of California, Santa Barbara; Google; Amazon
[56]. What Emotions Make One or Five Stars? Understanding Ratings of Online Product Reviews by Sentiment Analysis and XAI
鏈接 | https://arxiv.org/abs/2003.00201
作者 | Chaehan So
備註 | To be published in: Lecture Notes in Artificial Intelligence, 1st International Conference on Artificial Intelligence in HCI, AI-HCI, Held as Part of HCI International 2020, Kopenhagen, Denmark, July 19-24, Springer
2020年3月2日
[57]. Do all Roads Lead to Rome? Understanding the Role of Initialization in Iterative Back-Translation
鏈接 | https://arxiv.org/abs/2002.12867
作者 | Mikel Artetxe, Gorka Labaka, Noe Casas, Eneko Agirre
[58]. Metaphoric Paraphrase Generation
鏈接 | https://arxiv.org/abs/2002.12854
作者 | Kevin Stowe, Leonardo Ribeiro, Iryna Gurevych
[59]. UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
鏈接 | https://arxiv.org/abs/2002.12804
作者 | Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Songhao Piao, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon
單位 | Microsoft Research; Harbin Institute of Technology
[60]. Automatic Section Recognition in Obituaries
鏈接 | https://arxiv.org/abs/2002.12699
作者 | Valentino Sabbatino, Laura Bostan, Roman Klinger
備註 | 9 pages, 1 figure, accepted at LREC 2020
[61]. Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
鏈接 | https://arxiv.org/abs/2002.12645
作者 | Jennifer Williams, Joanna Rownicka, Pilar Oplustil, Simon King
單位 | University of Edinburgh
備註 | submitted to Odyssey 2020
[62]. TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing
鏈接 | https://arxiv.org/abs/2002.12620
作者 | Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
單位 | iFLYTEK Research; Harbin Institute of Technology
[63]. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding
鏈接 | https://arxiv.org/abs/2002.12591
作者 | Yuyu Zhang, Ping Nie, Xiubo Geng, Arun Ramamurthy, Le Song, Daxin Jiang
單位 | Georgia Institute of Technology; Peking University; Microsoft
[64]. Modeling Future Cost for Neural Machine Translation
鏈接 | https://arxiv.org/abs/2002.12558
作者 | Chaoqun Duan, Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Conghui Zhu, Tiejun Zhao
單位 | Harbin Institute of Technology
[65]. Robust Unsupervised Neural Machine Translation with Adversarial Training
鏈接 | https://arxiv.org/abs/2002.12549
作者 | Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao
單位 | Harbin Institute of Technology
[66]. UKARA 1.0 Challenge Track 1: Automatic Short-Answer Scoring in Bahasa Indonesia
鏈接 | https://arxiv.org/abs/2002.12540
作者 | Ali Akbar Septiandri, Yosef Ardhito Winatmoko
[67]. Temporal Convolutional Attention-based Network For Sequence Modeling
鏈接 | https://arxiv.org/abs/2002.12530
作者 | Hongyan Hao, Yan Wang, Yudi Xia, Jian Zhao, Furao Shen
單位 | Nanjing University
[68]. RP-DNN: A Tweet level propagation context based deep neural networks for early rumor detection in Social Media
鏈接 | https://arxiv.org/abs/2002.12683
作者 | Jie Gao, Sooji Han, Xingyi Song, Fabio Ciravegna
備註 | Manuscript accepted for publication at The LREC 2020 Proceedings.
[69]. A multi-layer approach to disinformation detection on Twitter
鏈接 | https://arxiv.org/abs/2002.12612
作者 | Francesco Pierri, Carlo Piccardi, Stefano Ceri
[70]. Exploring and Distilling Cross-Modal Information for Image Captioning
鏈接 | https://arxiv.org/abs/2002.12585
作者 | Fenglin Liu, Xuancheng Ren, Yuanxin Liu, Kai Lei, Xu Sun
單位 | Peking University; Beijing University of Posts and Telecommunications
[71]. Learning Directly from Grammar Compressed Text
鏈接 | https://arxiv.org/abs/2002.12570
作者 | Yoichi Sasaki, Kosuke Akimoto, Takanori Maehara
單位 | NEC Corporation
[72]. Comment Ranking Diversification in Forum Discussions
鏈接 | https://arxiv.org/abs/2002.12457
作者 | Curtis G. Northcutt, Kimberly A. Leon, Naichun Chen
單位 | MIT
備註 | published in Learning @ Scale, 2017
想要了解更多的自然語言處理最新進展、技術乾貨及學習教程，歡迎關注微信公衆號“語言智能技術筆記簿”或掃描二維碼添加關注。
