出品 | 深度學習這件小事公眾號
自然語言處理（12月25日更新版）
[1] I like fish, especially dolphins: Addressing Contradictions in Dialogue Modelling作者 | Yixin Nie, Mary Williamson, Mohit Bansal, Douwe Kiela, Jason Weston連結 | https://arxiv.org/abs/2012.13391 [2] To what extent do human explanations of model behavior align with actual model behavior?作者 | Grusha Prasad, Yixin Nie, Mohit Bansal, Robin Jia, Douwe Kiela, Adina Williams連結 | https://arxiv.org/abs/2012.13354 [3] A Context Aware Approach for Generating Natural Language Attacks作者 | Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi連結 | https://arxiv.org/abs/2012.13339 備註 | Accepted as Student Poster at AAAI 2021[4] Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification作者 | Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, Ting Liu連結 | https://arxiv.org/abs/2012.13260 備註 | Accepted by AAAI2021 (Long Paper). arXiv admin note: text overlap with arXiv:2008.06914[5] QUACKIE: A NLP Classification Task With Ground Truth Explanations作者 | Yves Rychener, Xavier Renard, Djamé Seddah, Pascal Frossard, Marcin Detyniecki連結 | https://arxiv.org/abs/2012.13190 [6] Sentence-Based Model Agnostic NLP Interpretability作者 | Yves Rychener, Xavier Renard, Djamé Seddah, Pascal Frossard, Marcin Detyniecki連結 | https://arxiv.org/abs/2012.13189 [7] REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement作者 | Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin連結 | https://arxiv.org/abs/2012.13185 備註 | Accepted by AAAI 2021[8] Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters作者 | Marta R. Costa-jussà, Carlos Escolano, Christine Basta, Javier Ferrando, Roser Batlle, Ksenia Kharitonova連結 | https://arxiv.org/abs/2012.13176 [9] Cross-lingual Dependency Parsing as Domain Adaptation作者 | Kailai Sun, Zuchao Li, Hai Zhao連結 | https://arxiv.org/abs/2012.13163 [10] SubICap: Towards Subword-informed Image Captioning作者 | Naeha Sharif, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah連結 | https://arxiv.org/abs/2012.13122 [11] ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language作者 | Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark連結 | https://arxiv.org/abs/2012.13048 [12] Multi-modal Identification of State-Sponsored Propaganda on Social Media作者 | Xiaobo Guo, Soroush Vosoughi連結 | https://arxiv.org/abs/2012.13042 備註 | Proceedings of the 25th International Conference on Pattern Recognition (ICPR 2020)[13] Disentangling semantics in language throughs VAEs and a certain architectural choice作者 | Ghazi Felhi, Joseph Le Roux, Djamé Seddah連結 | https://arxiv.org/abs/2012.13031 [14] Speech Synthesis as Augmentation for Low-Resource ASR作者 | Deblin Bagchi, Shannon Wotherspoon, Zhuolin Jiang, Prasanna Muthukumar連結 | https://arxiv.org/abs/2012.13004 [15] Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning作者 | Armen Aghajanyan, Luke Zettlemoyer, Sonal Gupta連結 | https://arxiv.org/abs/2012.13255 [16] Detecting Hateful Memes Using a Multimodal Deep Ensemble連結 | https://arxiv.org/abs/2012.13235 備註 | NeurIPS 2020, The Hateful Memes Challenge Workshop at NeurIPS 2020[17] Unsupervised neural adaptation model based on optimal transport for spoken language identification作者 | Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai連結 | https://arxiv.org/abs/2012.13152 [18] WEmbSim: A Simple yet Effective Metric for Image Captioning作者 | Naeha Sharif, Lyndon White, Mohammed Bennamoun, Wei Liu, Syed Afaq Ali Shah連結 | https://arxiv.org/abs/2012.13137 [19] Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs作者 | Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, Chandan K. Reddy連結 | https://arxiv.org/abs/2012.13023 [20] Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge作者 | Riza Velioglu, Jewgeni Rose連結 | https://arxiv.org/abs/2012.12975 備註 | Presented at NeurIPS (2020)下載1：四件套
在機器學習算法與自然語言處理公眾號後臺回復「四件套」，
即可獲取學習TensorFlow，Pytorch，機器學習，深度學習四件套！
下載2：倉庫地址共享
在機器學習算法與自然語言處理公眾號後臺回復「代碼」，
即可獲取195篇NAACL+295篇ACL2019有代碼開源的論文。開源地址如下：https://github.com/yizhen20133868/NLP-Conferences-Code
重磅！機器學習算法與自然語言處理交流群已正式成立！
群內有大量資源，歡迎大家進群學習！
額外贈送福利資源！深度學習與神經網絡，pytorch官方中文教程，利用Python進行數據分析，機器學習學習筆記，pandas官方文檔中文版，effective java（中文版）等20項福利資源
獲取方式：進入群後點開群公告即可領取下載連結
注意：請大家添加時修改備註為 [學校/公司 + 姓名 + 方向]
例如 —— 哈工大+張三+對話系統。
號主，微商請自覺繞道。謝謝！
推薦閱讀：
工業界求解NER問題的12條黃金法則
三步搞定機器學習核心：矩陣求導
神經網絡中的蒸餾技術，從Softmax開始說起