一周新论文 | 2020年第12周 | 自然语言处理相关

《一周新论文》系列之2020年第12周：自然语言处理相关

本周重点关注：

Google: [19]
Microsoft: [57]
其他: [26], [32], [50], [60]

2020年3月16日

[1]. Know thy corpus! Robust methods for digital curation of Web corpora
链接 | https://arxiv.org/abs/2003.06389
作者 | Serge Sharoff

[2]. Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks
链接 | https://arxiv.org/abs/2003.06381
作者 | Yu Yuan, Serge Sharoff

[3]. Using word embeddings to improve the discriminability of co-occurrence text networks
链接 | https://arxiv.org/abs/2003.06279
作者 | Laura V. C. Quispe, Jorge A. V. Tohalino, Diego R. Amancio

[4]. Review-guided Helpful Answer Identification in E-commerce
链接 | https://arxiv.org/abs/2003.06209
作者 | Wenxuan Zhang, Wai Lam, Yang Deng, Jing Ma
单位 | The Chinese University of Hong Kong
备注 | Accepted by WWW2020

[5]. WAC: A Corpus of Wikipedia Conversations for Online Abuse Detection
链接 | https://arxiv.org/abs/2003.06190
作者 | Noé Cecillon (LIA), Vincent Labatut (LIA), Richard Dufour (LIA), Georges Linares (LIA)

[6]. MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
链接 | https://arxiv.org/abs/2003.06094
作者 | Xiaoyuan Yi, Ruoyu Li, Cheng Yang, Wenhao Li, Maosong Sun
单位 | Tsinghua University; Beijing University of Posts and Telecommunications
备注 | 8 pages, 5 figures, published in AAAI 2020

[7]. Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition
链接 | https://arxiv.org/abs/2003.06044
作者 | Zhigang Dai, Jinhua Fu, Qile Zhu, Hengbin Cui, Xiaolong li, Yuan Qi
单位 | South China University of Technology; Ant Financial Service Group

[8]. Efficient Rule Learning with Template Saturation for Knowledge Graph Completion
链接 | https://arxiv.org/abs/2003.06071
作者 | Yulong Gu, Yu Guan, Paolo Missier

[9]. Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning
链接 | https://arxiv.org/abs/2003.06050
作者 | Mandana Saebi, Steven Krieg, Chuxu Zhang, Meng Jiang, Nitesh Chawla
单位 | University of Notre Dame

[10]. CRWIZ: A Framework for Crowdsourcing Real-Time Wizard-of-Oz Dialogues
链接 | https://arxiv.org/abs/2003.05995
作者 | Francisco J. Chiyah Garcia, José Lopes, Xingkun Liu, Helen Hastie
备注 | 10 pages, 5 figures. To Appear in LREC 2020

2020年3月17日

[11]. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
链接 | https://arxiv.org/abs/2003.07082
作者 | Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning
单位 | Stanford University

[12]. Key Phrase Classification in Complex Assignments
链接 | https://arxiv.org/abs/2003.07019
作者 | Manikandan Ravikiran

[13]. CompLex — A New Corpus for Lexical Complexity Predicition from Likert Scale Data
链接 | https://arxiv.org/abs/2003.07008
作者 | Matthew Shardlow, Michael Cooper, Marcos Zampieri

[14]. TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding
链接 | https://arxiv.org/abs/2003.07000
作者 | Zhiheng Huang, Peng Xu, Davis Liang, Ajay Mishra, Bing Xiang
单位 | Amazon AWS AI

[15]. Synonymous Generalization in Sequence-to-Sequence Recurrent Networks
链接 | https://arxiv.org/abs/2003.06658
作者 | Ning Shi
单位 | Georgia Institute of Technology

[16]. Word Sense Disambiguation for 158 Languages using Word Embeddings Only
链接 | https://arxiv.org/abs/2003.06651
作者 | Varvara Logacheva, Denis Teslenko, Artem Shelmanov, Steffen Remus, Dmitry Ustalov, Andrey Kutuzov, Ekaterina Artemova, Chris Biemann, Simone Paolo Ponzetto, Alexander Panchenko

[17]. Text Similarity Using Word Embeddings to Classify Misinformation
链接 | https://arxiv.org/abs/2003.06634
作者 | Caio Almeida, Débora Santos

[18]. LSCP: Enhanced Large Scale Colloquial Persian Language Understanding
链接 | https://arxiv.org/abs/2003.06499
作者 | Hadi Abdi Khojasteh, Ebrahim Ansari, Mahdi Bohlouli
备注 | 6 pages, 2 figures, 3 tables, Accepted at the 12th International Conference on Language Resources and Evaluation (LREC 2020)

[19]. A Survey on Contextual Embeddings
链接 | https://arxiv.org/abs/2003.07278
作者 | Qi Liu, Matt J. Kusner, Phil Blunsom
单位 | University of Oxford; DeepMind; University College London; The Alan Turing Institute

[20]. A Machine Learning Application for Raising WASH Awareness in the Times of Covid-19 Pandemic
链接 | https://arxiv.org/abs/2003.07074
作者 | Rohan Pandey, Vaibhav Gautam, Kanav Bhagat, Tavpritesh Sethi

[21]. Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models
链接 | https://arxiv.org/abs/2003.06894
作者 | Natalia Tomashenko, Yuri Khokhlov, Yannick Esteve

[22]. Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
链接 | https://arxiv.org/abs/2003.06686
作者 | Zack Hodari, Catherine Lai, Simon King
单位 | University of Edinburgh

[23]. Counterfactual Samples Synthesizing for Robust Visual Question Answering
链接 | https://arxiv.org/abs/2003.06576
作者 | Long Chen, Xin Yan, Jun Xiao, Hanwang Zhang, Shiliang Pu, Yueting Zhuang
单位 | Zhejiang University; Nanyang Technological University
备注 | Appear in CVPR 2020;

[24]. Semantically-Enriched Search Engine for Geoportals: A Case Study with ArcGIS Online
链接 | https://arxiv.org/abs/2003.06561
作者 | Gengchen Mai, Krzysztof Janowicz, Sathya Prasad, Meilin Shi, Ling Cai, Rui Zhu, Blake Regalia, Ni Lao

[25]. DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains
链接 | https://arxiv.org/abs/2003.06514
作者 | Chang Xu, Cecile Paris, Surya Nepal, Ross Sparks, Chong Long, Yafang Wang
备注 | Accepted at ECAI2020

2020年3月18日

[26]. Rethinking Batch Normalization in Transformers
链接 | https://arxiv.org/abs/2003.07845
作者 | Sheng Shen, Zhewei Yao, Amir Gholami, Michael Mahoney, Kurt Keutzer
单位 | UC Berkeley

[27]. A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
链接 | https://arxiv.org/abs/2003.07743
作者 | Zequn Sun, Qingheng Zhang, Wei Hu, Chengming Wang, Muhao Chen, Farahnaz Akrami, Chengkai Li
单位 | Nanjing University; UCLA; University of Texas at Arlington

[28]. PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry
链接 | https://arxiv.org/abs/2003.07723
作者 | Thomas Haider, Steffen Eger, Evgeny Kim, Roman Klinger, Winfried Menninghaus

[29]. Adapting Deep Learning Methods for Mental Health Prediction on Social Media
链接 | https://arxiv.org/abs/2003.07634
作者 | Ivan Sekulić, Michael Strube
备注 | W-NUT at EMNLP 2019

[30]. XPersona: Evaluating Multilingual Personalized Chatbot
链接 | https://arxiv.org/abs/2003.07568
作者 | Zhaojiang Lin, Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Yejin Bang, Etsuko Ishii, Pascale Fung
单位 | Hong Kong University of Science and Technology

[31]. Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes
链接 | https://arxiv.org/abs/2003.07507
作者 | A.K. Bhavani Singh, Mounika Guntu, Ananth Reddy Bhimireddy, Judy W. Gichoya, Saptarshi Purkayastha
备注 | This is a shortened version of the Capstone Project that was accepted by the Faculty of Indiana University, in partial fulfillment of the requirements for the degree of Master of Science in Health Informatics

[32]. Recent Advances and Challenges in Task-oriented Dialog System
链接 | https://arxiv.org/abs/2003.07490
作者 | Zheng Zhang, Ryuichi Takanobu, Minlie Huang, Xiaoyan Zhu
单位 | Tsinghua University
备注 | Under review of Science China Information Science

[33]. Offensive Language Identification in Greek
链接 | https://arxiv.org/abs/2003.07459
作者 | Zeses Pitenis, Marcos Zampieri, Tharindu Ranasinghe
备注 | Accepted to LREC 2020

[34]. HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment
链接 | https://arxiv.org/abs/2003.07456
作者 | Anssi Yli-Jyrä, Josi Purhonen, Matti Liljeqvist, Arto Antturi, Pekka Nieminen, Kari M. Räntilä, Valtter Luoto
备注 | 8 pages, 3 tables, to appear in the Language Resources and Evaluation Conference (LREC) 2020

[35]. A Label Proportions Estimation technique for Adversarial Domain Adaptation in Text Classification
链接 | https://arxiv.org/abs/2003.07444
作者 | Zhuohao Chen; Karan Singla; David C. Atkins; Zac E Imel
单位 | University of Southern California; University of Washington; University of Utah

[36]. LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment
链接 | https://arxiv.org/abs/2003.07433
作者 | Mohammad Arif Ul Alam, Dhawal Kapadia
备注 | Submitted in SmartComp 2020

[37]. Developing a Multilingual Annotated Corpus of Misogyny and Aggression
链接 | https://arxiv.org/abs/2003.07428
作者 | Shiladitya Bhattacharya, Siddharth Singh, Ritesh Kumar, Akanksha Bansal, Akash Bhagat, Yogesh Dawer, Bornini Lahiri, Atul Kr. Ojha
备注 | Submitted for review to Second Workshop on Trolling, Aggression and Cyberbullying (TRAC 2020)

[38]. Parallel sequence tagging for concept recognition
链接 | https://arxiv.org/abs/2003.07424
作者 | Lenz Furrer, Joseph Cornelius, Fabio Rinaldi
单位 | University of Zurich

[39]. A Formal Analysis of Multimodal Referring Strategies Under Common Ground
链接 | https://arxiv.org/abs/2003.07385
作者 | Nikhil Krishnaswamy, James Pustejovsky

[40]. Overview of the TREC 2019 deep learning track
链接 | https://arxiv.org/abs/2003.07820
作者 | Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, Ellen M. Voorhees
单位 | Microsoft; University College London

[41]. Multi-modal Dense Video Captioning
链接 | https://arxiv.org/abs/2003.07758
作者 | Vladimir Iashin, Esa Rahtu

[42]. Hybrid Autoregressive Transducer (hat)
链接 | https://arxiv.org/abs/2003.07705
作者 | Ehsan Variani, David Rybach, Cyril Allauzen, Michael Riley
单位 | Google

[43]. Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice
链接 | https://arxiv.org/abs/2003.07683
作者 | Chaehan So
备注 | To be published in IEEE conference proceedings: International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2020

[44]. High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
链接 | https://arxiv.org/abs/2003.07482
作者 | Jinyu Li, Rui Zhao, Eric Sun, Jeremy H. M. Wong, Amit Das, Zhong Meng, Yifan Gong
单位 | Microsoft
备注 | Accepted by ICASSP 2020

[45]. Harnessing Explanations to Bridge AI and Humans
链接 | https://arxiv.org/abs/2003.07370
作者 | Vivian Lai, Samuel Carton, Chenhao Tan
单位 | University of Colorado Boulder

2020年3月19日

[46]. X-Stance: A Multilingual Multi-Target Dataset for Stance Detection
链接 | https://arxiv.org/abs/2003.08385
作者 | Jannis Vamvas, Rico Sennrich
单位 | University of Zurich; University of Edinburgh

[47]. TTTTTackling WinoGrande Schemas
链接 | https://arxiv.org/abs/2003.08380
作者 | Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
单位 | University of Waterloo

[48]. Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
链接 | https://arxiv.org/abs/2003.08370
作者 | David Ifeoluwa Adelani, Michael A. Hedderich, Dawei Zhu, Esther van den Berg, Dietrich Klakow
备注 | Accepted to ICLR 2020 Workshop

[49]. Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training
链接 | https://arxiv.org/abs/2003.08272
作者 | Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, Vera Demberg
备注 | Accepted to Workshop at ICLR 2020

[50]. Pre-trained Models for Natural Language Processing: A Survey
链接 | https://arxiv.org/abs/2003.08271
作者 | Xipeng Qiu, Tianxiang Sun, Yige Xu, Yunfan Shao, Ning Dai, Xuanjing Huang
单位 | Fudan University
备注 | Invited Review of Science China Technological Sciences

[51]. Gender Representation in Open Source Speech Resources
链接 | https://arxiv.org/abs/2003.08132
作者 | Mahault Garnerin, Solange Rossato, Laurent Besacier
备注 | accepted to LREC2020

[52]. Calibration of Pre-trained Transformers
链接 | https://arxiv.org/abs/2003.07892
作者 | Shrey Desai, Greg Durrett
单位 | University of Texas at Austin

[53]. Anchor & Transform: Learning Sparse Representations of Discrete Objects
链接 | https://arxiv.org/abs/2003.08197
作者 | Paul Pu Liang, Manzil Zaheer, Yuan Wang, Amr Ahmed

[54]. Deliberation Model Based Two-Pass End-to-End Speech Recognition
链接 | https://arxiv.org/abs/2003.07962
作者 | Ke Hu, Tara N. Sainath, Ruoming Pang, Rohit Prabhavalkar
单位 | Google

2020年3月20日

[55]. Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent
链接 | https://arxiv.org/abs/2003.08925
作者 | Anoop Kunchukuttan, Pushpak Bhattacharyya
备注 | This work was done in 2017-2018 as part of the first author’s thesis

[56]. Beheshti-NER: Persian Named Entity Recognition Using BERT
链接 | https://arxiv.org/abs/2003.08875
作者 | Ehsan Taher, Seyed Abbas Hoseini, Mehrnoush Shamsfard

[57]. Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph
链接 | https://arxiv.org/abs/2003.08612
作者 | Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang
单位 | Microsoft; University of Notre Dame

[58]. Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections
链接 | https://arxiv.org/abs/2003.08529
作者 | Yi-An Lai, Xuan Zhu, Yi Zhang, Mona Diab
单位 | AWS; The George Washington University
备注 | Accepted by LREC 2020

[59]. An Analysis on the Learning Rules of the Skip-Gram Model
链接 | https://arxiv.org/abs/2003.08489
作者 | Canlin Zhang, Xiuwen Liu, Daniel Bis
备注 | Published on the 2019 International Joint Conference on Neural Networks

[60]. Normalized and Geometry-Aware Self-Attention Network for Image Captioning
链接 | https://arxiv.org/abs/2003.08897
作者 | Longteng Guo, Jing Liu, Xinxin Zhu, Peng Yao, Shichen Lu, Hanqing Lu
单位 | Chinese Academy of Sciences; University of Science and Technology Beijing; Wuhan University
备注 | Accepted by CVPR 2020

[61]. Deep Learning for Automatic Tracking of Tongue Surface in Real-time Ultrasound Videos, Landmarks instead of Contours
链接 | https://arxiv.org/abs/2003.08808
作者 | M. Hamed Mozaffari, Won-Sook Lee

[62]. Personalized Taste and Cuisine Preference Modeling via Images
链接 | https://arxiv.org/abs/2003.08769
作者 | Nitish Nag, Bindu Rajanna, Ramesh Jain

[63]. Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding
链接 | https://arxiv.org/abs/2003.08717
作者 | Thierry Deruyttere, Guillem Collell, Marie-Francine Moens

[64]. QnAMaker: Data to Bot in 2 Minutes
链接 | https://arxiv.org/abs/2003.08553
作者 | Parag Agrawal, Tulasi Menon, Aya Kamel, Michel Naim, Chaikesh Chouragade, Gurvinder Singh, Rohan Kulkarni, Anshuman Suri, Sahithi Katakam, Vineet Pratik, Prakul Bansal, Simerpreet Kaur, Neha Rajput, Anand Duggal, Achraf Chalabi, Prashant Choudhari, Reddy Satti, Niranjan Nayak
单位 | Microsoft
备注 | Published at The Web Conference 2020 in the demo track

[65]. A Corpus of Adpositional Supersenses for Mandarin Chinese
链接 | https://arxiv.org/abs/2003.08437
作者 | Siyao Peng, Yang Liu, Yilun Zhu, Austin Blodgett, Yushi Zhao, Nathan Schneider
单位 | Georgetown University

想要了解更多的自然语言处理最新进展、技术干货及学习教程，欢迎关注微信公众号“语言智能技术笔记簿”或扫描二维码添加关注。