每日论文速递:自然语言处理相关(10月26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(10月26日更新版)
[1] DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries
作者 | Aditi Chaudhary, Karthik Raman, Krishna Srinivasan, Jiecao Chen
链接 | https://arxiv.org/abs/2010.12566
[2] Customizing Triggers with Concealed Data Poisoning
作者 | Eric Wallace, Tony Z. Zhao, Shi Feng, Sameer Singh
链接 | https://arxiv.org/abs/2010.12563
[3] On the Transformer Growth for Progressive BERT Training
作者 | Xiaotao Gu, Liyuan Liu, Hongkun Yu, Jing Li, Chen Chen, Jiawei Han
链接 | https://arxiv.org/abs/2010.12562
[4] Multilingual BERT Post-Pretraining Alignment
作者 | Lin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Mo Yu, Saloni Potdar
链接 | https://arxiv.org/abs/2010.12547
[5] GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method
作者 | Nicole Peinelt, Marek Rei, Maria Liakata
链接 | https://arxiv.org/abs/2010.12532
[6] Retrieve, Rerank, Read, then Iterate: Answering Open-Domain Questions of Arbitrary Complexity from Text
作者 | Peng Qi, Haejun Lee, Oghenetegiri "TG" Sido, Christopher D. Manning
链接 | https://arxiv.org/abs/2010.12527
备注 | Peng Qi and Haejun Lee contributed equally
[7] Neural Passage Retrieval with Improved Negative Contrast
作者 | Jing Lu, Gustavo Hernandez Abrego, Ji Ma, Jianmo Ni, Yinfei Yang
链接 | https://arxiv.org/abs/2010.12523
[8] Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification
作者 | Linyi Yang, Eoin M. Kenny, Tin Lok James Ng, Yi Yang, Barry Smyth, Ruihai Dong
链接 | https://arxiv.org/abs/2010.12512
备注 | Accepted by COLING-20 (Oral)
[9] Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures
作者 | Nafise Sadat Moosavi, Marcel de Boer, Prasetya Ajie Utama, Iryna Gurevych
链接 | https://arxiv.org/abs/2010.12510
[10] Helping users discover perspectives: Enhancing opinion mining with joint topic models
作者 | Tim Draws, Jody Liu, Nava Tintarev
链接 | https://arxiv.org/abs/2010.12505
备注 | Accepted at the SENTIRE workshop at ICDM 2020
[11] Understanding the Extent to which Summarization Evaluation Metrics Measure the Information Quality of Summaries
作者 | Daniel Deutsch, Dan Roth
链接 | https://arxiv.org/abs/2010.12495
[12] Intrinsic Quality Assessment of Arguments
作者 | Henning Wachsmuth, Till Werner
链接 | https://arxiv.org/abs/2010.12473
备注 | Accepted at COLING 2020
[13] HateBERT: Retraining BERT for Abusive Language Detection in English
作者 | Tommaso Caselli, Valerio Basile, Jelena Mitrović, Michael Granitzer
链接 | https://arxiv.org/abs/2010.12472
[14] Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-resourced Languages
作者 | Diego Alves, Gaurish Thakkar, Marko Tadić
链接 | https://arxiv.org/abs/2010.12433
[15] Evaluating Language Tools for Fifteen EU-official Under-resourced Languages
作者 | Diego Alves, Gaurish Thakkar, Marko Tadić
链接 | https://arxiv.org/abs/2010.12428
[16] TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification
作者 | Francesco Barbieri, Jose Camacho-Collados, Leonardo Neves, Luis Espinosa-Anke
链接 | https://arxiv.org/abs/2010.12421
备注 | Findings of EMNLP 2020.
[17] Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls
作者 | Ahmed Ghanim Al-Ali, Robert Phaal, Donald Sull
链接 | https://arxiv.org/abs/2010.12418
备注 | Accepted for The 28th International Conference on Computational Linguistics, 9 pages, 1 figure
[18] SmBoP: Semi-autoregressive Bottom-up Semantic Parsing
作者 | Ohad Rubin, Jonathan Berant
链接 | https://arxiv.org/abs/2010.12412
[19] UNER: Universal Named-Entity RecognitionFramework
作者 | Diego Alves, Tin Kuculo, Gabriel Amaral, Gaurish Thakkar, Marko Tadic
链接 | https://arxiv.org/abs/2010.12406
[20] Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond
作者 | Xin Li, Lidong Bing, Wenxuan Zhang, Zheng Li, Wai Lam
链接 | https://arxiv.org/abs/2010.12405
[21] Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets
作者 | Gaurish Thakkar, Marcis Pinnis
链接 | https://arxiv.org/abs/2010.12401
[22] NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction
作者 | Lukas Lange, Xiang Dai, Heike Adel, Jannik Strötgen
链接 | https://arxiv.org/abs/2010.12322
备注 | IberLEF 2020
[23] BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
作者 | Moussa Kamal Eddine, Antoine J.-P. Tixier, Michalis Vazirgiannis
链接 | https://arxiv.org/abs/2010.12321
[24] A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios
作者 | Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow
链接 | https://arxiv.org/abs/2010.12309
[25] Adversarial Learning of Feature-based Meta-Embeddings
作者 | Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow
链接 | https://arxiv.org/abs/2010.12305
[26] ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding
作者 | Minjeong Kim, Gyuwan Kim, Sang-Woo Lee, Jung-Woo Ha
链接 | https://arxiv.org/abs/2010.12283
[27] Pre-trained Model for Chinese Word Segmentation with Meta Learning
作者 | Zhen Ke, Liang Shi, Erli Meng, Bin Wang, Xipeng Qiu
链接 | https://arxiv.org/abs/2010.12272
[28] A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems
作者 | Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya
链接 | https://arxiv.org/abs/2010.12251
[29] Proof-theoretic aspects of NLλ
作者 | Richard Moot (TEXTE, LIRMM, CNRS)
链接 | https://arxiv.org/abs/2010.12223
[30] Domain Divergences: a Survey and Empirical Analysis
作者 | Abhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann
链接 | https://arxiv.org/abs/2010.12198
[31] Identifying Similar Movie Characters Quickly but Effectively Using Non-exhaustive Pair-wise Attention
作者 | Zhilin Wang, Weizhe Lin, Xiaodong Wu
链接 | https://arxiv.org/abs/2010.12183
[32] KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
作者 | Rubungo Andre Niyongabo, Hong Qu, Julia Kreutzer, Li Huang
链接 | https://arxiv.org/abs/2010.12174
备注 | COLING 2020
[33] Attention Transfer Network for Aspect-level Sentiment Classification
作者 | Fei Zhao, Zhen Wu, Xinyu Dai
链接 | https://arxiv.org/abs/2010.12156
备注 | Accept to COLING 2020
[34] ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
作者 | Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
链接 | https://arxiv.org/abs/2010.12148
备注 | work-in-progress
[35] Summarizing Utterances from Japanese Assembly Minutes using Political Sentence-BERT-based Method for QA Lab-PoliInfo-2 Task of NTCIR-15
作者 | Daiki Shirafuji, Hiromichi Kameya, Rafal Rzepka, Kenji Araki
链接 | https://arxiv.org/abs/2010.12077
备注 | NTCIR-15 conference
[36] Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension
作者 | Siamak Shakeri, Noah Constant, Mihir Sanjay Kale, Linting Xue
链接 | https://arxiv.org/abs/2010.12008
[37] Meta-Learning for Domain Generalization in Semantic Parsing
作者 | Bailin Wang, Mirella Lapata, Ivan Titov
链接 | https://arxiv.org/abs/2010.11988
备注 | V1.0
[38] MTGAT: Multimodal Temporal Graph Attention Networks for Unaligned Human Multimodal Language Sequences
作者 | Jianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu, Azaan Rehman, Amir Zadeh, Soujanya Poria, Louis-Philippe Morency
链接 | https://arxiv.org/abs/2010.11985
[39] The Turking Test: Can Language Models Understand Instructions?
作者 | Avia Efrat, Omer Levy
链接 | https://arxiv.org/abs/2010.11982
[40] A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents
作者 | Tuan Manh Lai, Trung Bui, Doo Soon Kim, Quan Hung Tran
链接 | https://arxiv.org/abs/2010.11980
备注 | Accepted to COLING 2020
[41] Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification
作者 | Badr M. Abdullah, Jacek Kudera, Tania Avgustinova, Bernd Möbius, Dietrich Klakow
链接 | https://arxiv.org/abs/2010.11973
备注 | Accepted in VarDial 2020 Workshop
[42] Language Models are Open Knowledge Graphs
作者 | Chenguang Wang, Xiao Liu, Dawn Song
链接 | https://arxiv.org/abs/2010.11967
[43] Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data
作者 | David Lowell, Brian E. Howard, Zachary C. Lipton, Byron C. Wallace
链接 | https://arxiv.org/abs/2010.11966
[44] A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric
作者 | Zekun Xu, Abhinav Aggarwal, Oluwaseyi Feyisetan, Nathanael Teissier
链接 | https://arxiv.org/abs/2010.11947
[45] EML System Description for VoxCeleb Speaker Diarization Challenge 2020
作者 | Omid Ghahabi, Volker Fischer
链接 | https://arxiv.org/abs/2010.12497
[46] An Analysis of LIME for Text Data
作者 | Dina Mardaoui, Damien Garreau
链接 | https://arxiv.org/abs/2010.12487
[47] Show and Speak: Directly Synthesize Spoken Description of Images
作者 | Xinsheng Wang, Siyuan Feng, Jihua Zhu, Mark Hasegawa-Johnson, Odette Scharenborg
链接 | https://arxiv.org/abs/2010.12267
[48] Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representations
作者 | Wen-Chin Huang, Yi-Chiao Wu, Tomoki Hayashi, Tomoki Toda
链接 | https://arxiv.org/abs/2010.12231
备注 | Submitted to ICASSP 2021
[49] Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
作者 | Sanyuan Chen, Yu Wu, Zhuo Chen, Takuya Yoshioka, Shujie Liu, Jinyu Li
链接 | https://arxiv.org/abs/2010.12180
[50] Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention
作者 | Menglong Xu, Shengqiang Li, Xiao-Lei Zhang
链接 | https://arxiv.org/abs/2010.12155
[51] Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
作者 | Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz
链接 | https://arxiv.org/abs/2010.12136
备注 | NeurIPS 2020
[52] Knowledge Graph Embedding with Atrous Convolution and Residual Learning
作者 | Feiliang Ren, Juchen Li, Huihui Zhang, Shilei Liu, Bochao Li, Ruicheng Ming, Yujia Bai
链接 | https://arxiv.org/abs/2010.12121
[53] How Phonotactics Affect Multilingual and Zero-shot ASR Performance
作者 | Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
链接 | https://arxiv.org/abs/2010.12104
备注 | Submitted to ICASSP 2021. The first 2 authors contributed equally to this work
[54] Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data
作者 | Thibault Doutre, Wei Han, Min Ma, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Arun Narayanan, Ananya Misra, Yu Zhang, Liangliang Cao
链接 | https://arxiv.org/abs/2010.12096
[55] Language-Conditioned Imitation Learning for Robot Manipulation Tasks
作者 | Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Stefan Lee, Chitta Baral, Heni Ben Amor
链接 | https://arxiv.org/abs/2010.12083
备注 | Accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada as spotlight presentation
[56] Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset
作者 | Zhanwen Chen, Shiyao Li, Roxanne Rashedi, Xiaoman Zi, Morgan Elrod-Erickson, Bryan Hollis, Angela Maliakal, Xinyu Shen, Simeng Zhao, Maithilee Kunda
链接 | https://arxiv.org/abs/2010.11997
备注 | To appear in the Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL), 2020
[57] The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker Diarisation Challenge
作者 | Renyu Wang, Ruilin Tong, Yu Ting Yeung, Xiao Chen
链接 | https://arxiv.org/abs/2010.11657
备注 | 5 pages, 2 figures, A report about our diarisation system for VoxCeleb Challenge, Interspeech conference workshop
—完—
最新评论
推荐文章
作者最新文章
你可能感兴趣的文章
Copyright Disclaimer: The copyright of contents (including texts, images, videos and audios) posted above belong to the User who shared or the third-party website which the User shared from. If you found your copyright have been infringed, please send a DMCA takedown notice to [email protected]. For more detail of the source, please click on the button "Read Original Post" below. For other communications, please send to [email protected].
版权声明:以上内容为用户推荐收藏至CareerEngine平台,其内容(含文字、图片、视频、音频等)及知识版权均属用户或用户转发自的第三方网站,如涉嫌侵权,请通知[email protected]进行信息删除。如需查看信息来源,请点击“查看原文”。如需洽谈其它事宜,请联系[email protected]。
版权声明:以上内容为用户推荐收藏至CareerEngine平台,其内容(含文字、图片、视频、音频等)及知识版权均属用户或用户转发自的第三方网站,如涉嫌侵权,请通知[email protected]进行信息删除。如需查看信息来源,请点击“查看原文”。如需洽谈其它事宜,请联系[email protected]。