出品 | 深度學習這件小事公眾號
自然語言處理（11月17日更新版）
[1] Learning from Task Descriptions作者 | Orion Weller, Nicholas Lourie, Matt Gardner, Matthew E. Peters連結 | https://arxiv.org/abs/2011.08115 [2] A Dataset for Tracking Entities in Open Domain Procedural Text作者 | Niket Tandon, Keisuke Sakaguchi, Bhavana Dalvi Mishra, Dheeraj Rajagopal, Peter Clark, Michal Guerquin, Kyle Richardson, Eduard Hovy連結 | https://arxiv.org/abs/2011.08092 備註 | To appear in EMNLP 2020[3] Tweet Sentiment Quantification: An Experimental Re-Evaluation作者 | Alejandro Moreo, Fabrizio Sebastiani連結 | https://arxiv.org/abs/2011.08091 [4] Answer Identification in Collaborative Organizational Group Chat作者 | Naama Tepper, Naama Zwerdling, David Naori, Inbal Ronen連結 | https://arxiv.org/abs/2011.08074 [5] Analyzing Sustainability Reports Using Natural Language Processing作者 | Alexandra Luccioni, Emily Bailor, Nicolas Duchene連結 | https://arxiv.org/abs/2011.08073 [6] Topic-Centric Unsupervised Multi-Document Summarization of Scientific and News Articles作者 | Amanuel Alambo, Cori Lohstroh, Erik Madaus, Swati Padhee, Brandy Foster, Tanvi Banerjee, Krishnaprasad Thirunarayan, Michael Raymer連結 | https://arxiv.org/abs/2011.08072 備註 | 6 pages, 6 Figures, 8 Tables. Accepted at IEEE Big Data 2020[7] JNLP Team: Deep Learning for Legal Processing in COLIEE 2020作者 | Ha-Thanh Nguyen, Hai-Yen Thi Vuong, Phuong Minh Nguyen, Binh Tran Dang, Quan Minh Bui, Sinh Trong Vu, Chau Minh Nguyen, Vu Tran, Ken Satoh, Minh Le Nguyen連結 | https://arxiv.org/abs/2011.08071 備註 | Also be published in JURISIN2020[8] Hierarchical Transformer for Task Oriented Dialog Systems作者 | Bishal Santra, Potnuru Anusha, Pawan Goyal連結 | https://arxiv.org/abs/2011.08067 [9] "What is on your mind?" Automated Scoring of Mindreading in Childhood and Early Adolescence作者 | Venelin Kovatchev, Phillip Smith, Mark Lee, Imogen Grumley Traynor, Irene Luque Aguilera, Rory T. Devine連結 | https://arxiv.org/abs/2011.08035 備註 | Accepted in COLING 2020[10] Comparative Probing of Lexical Semantics Theories for Cognitive Plausibility and Technological Usefulness作者 | António Branco, João Rodrigues, Małgorzata Salawa, Ruben Branco, Chakaveh Saedi連結 | https://arxiv.org/abs/2011.07997 [11] The Person Index Challenge: Extraction of Persons from Messy, Short Texts作者 | Markus Schröder, Christian Jilek, Michael Schulze, Andreas Dengel連結 | https://arxiv.org/abs/2011.07990 備註 | 7 pages, accepted at ICAART 2021[12] Datasets and Models for Authorship Attribution on Italian Personal Writings作者 | Gaetana Ruggiero, Albert Gatt, Malvina Nissim連結 | https://arxiv.org/abs/2011.07975 備註 | Accepted for publication in: 7th Italian Conference on Computational Linguistics (CLIC-IT 2020)[13] Learning from similarity and information extraction from structured documents連結 | https://arxiv.org/abs/2011.07964 備註 | 8 pages, 4 figures, manuscript for the IJDAR journal special issue for ICDAR conference[14] Performance of Transfer Learning Model vs. Traditional Neural Network in Low System Resource Environment連結 | https://arxiv.org/abs/2011.07962 備註 | 5 pages, testing result, feature engineering[15] An Empirical Investigation of Contextualized Number Prediction作者 | Daniel Spokoyny, Taylor Berg-Kirkpatrick連結 | https://arxiv.org/abs/2011.07961 [16] Explicitly Modeling Syntax in Language Model improves Generalization作者 | Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville連結 | https://arxiv.org/abs/2011.07960 備註 | 12 pages, 10 figures[17] Pre-training Text-to-Text Transformers for Concept-centric Common Sense作者 | Wangchunshu Zhou, Dong-Ho Lee, Ravi Kiran Selvam, Seyeon Lee, Bill Yuchen Lin, Xiang Ren連結 | https://arxiv.org/abs/2011.07956 項目連結 | https://github.com/INK-USC/CALM/[18] Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions作者 | Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Tawfik, Hany Hassan Awadalla連結 | https://arxiv.org/abs/2011.07933 備註 | Accepted at WMT20 (EMNLP 2020 Fifth Conference on Machine Translation)[19] Text Information Aggregation with Centrality Attention作者 | Jingjing Gong, Hang Yan, Yining Zheng, Xipeng Qiu, Xuanjing Huang連結 | https://arxiv.org/abs/2011.07916 [20] Evaluating Sentence Segmentation and Word Tokenization Systems on Estonian Web Texts作者 | Kairit Sirts, Kairit Peekman連結 | https://arxiv.org/abs/2011.07868 [21] WikiAsp: A Dataset for Multi-domain Aspect-based Summarization作者 | Hiroaki Hayashi, Prashant Budania, Peng Wang, Chris Ackerson, Raj Neervannan, Graham Neubig連結 | https://arxiv.org/abs/2011.07832 備註 | Transaction of the ACL[22] Deep Shallow Fusion for RNN-T Personalization作者 | Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer連結 | https://arxiv.org/abs/2011.07754 備註 | To appear at SLT 2021[23] Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases作者 | Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, Yu Su連結 | https://arxiv.org/abs/2011.07743 [24] Reinforced Medical Report Generation with X-Linear Attention and Repetition Penalty作者 | Wenting Xu, Chang Qi, Zhenghua Xu, Thomas Lukasiewicz連結 | https://arxiv.org/abs/2011.07680 [25] IIT_kgp at FinCausal 2020, Shared Task 1: Causality Detection using Sentence Embeddings in Financial Reports作者 | Arka Mitra, Harshvardhan Srivastava, Yugam Tiwari連結 | https://arxiv.org/abs/2011.07670 [26] ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments作者 | Hyounghun Kim, Abhay Zala, Graham Burri, Hao Tan, Mohit Bansal連結 | https://arxiv.org/abs/2011.07660 備註 | EMNLP Findings 2020 (18 pages; extended to Hindi)[27] DORB: Dynamically Optimizing Multiple Rewards with Bandits作者 | Ramakanth Pasunuru, Han Guo, Mohit Bansal連結 | https://arxiv.org/abs/2011.07635 備註 | EMNLP 2020 (15 pages)[28] The Challenge of Diacritics in Yoruba Embeddings作者 | Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki連結 | https://arxiv.org/abs/2011.07605 備註 | Presented at NeurIPS 2020 Workshop on Machine Learning for the Developing World[29] Morphologically Aware Word-Level Translation作者 | Paula Czarnowska, Sebastian Ruder, Ryan Cotterell, Ann Copestake連結 | https://arxiv.org/abs/2011.07593 [30] Target Guided Emotion Aware Chat Machine作者 | Wei Wei, Jiayi Liu, Xianling Mao, Guibin Guo, Feida Zhu, Pan Zhou, Yuchong Hu, Shanshan Feng連結 | https://arxiv.org/abs/2011.07432 [31] Iterative Self-Learning for Enhanced Back-Translation in Low Resource Neural Machine Translation作者 | Idris Abdulmumin, Bashir Shehu Galadanci, Ismaila Idris Sinan連結 | https://arxiv.org/abs/2011.07403 [32] Lessons from Computational Modelling of Reference Production in Mandarin and English作者 | Guanyi Chen, Kees van Deemter連結 | https://arxiv.org/abs/2011.07398 備註 | Long paper accepted at INLG 2020[33] Words are the Window to the Soul: Language-based User Representations for Fake News Detection作者 | Marco Del Tredici, Raquel Fernández連結 | https://arxiv.org/abs/2011.07389 備註 | 9 pages, accepted at COLING 2020[34] Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration作者 | Fan-Keng Sun, Cheng-I Lai連結 | https://arxiv.org/abs/2011.07347 [35] Meaningful Answer Generation of E-Commerce Question-Answering作者 | Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, Rui Yan連結 | https://arxiv.org/abs/2011.07307 [36] Sentiment Analysis for Sinhala Language using Deep Learning Techniques作者 | Lahiru Senevirathne, Piyumal Demotte, Binod Karunanayake, Udyogi Munasinghe, Surangika Ranathunga連結 | https://arxiv.org/abs/2011.07280 [37] DebateSum: A large-scale argument mining and summarization dataset作者 | Allen Roush, Arvind Balaji連結 | https://arxiv.org/abs/2011.07251 備註 | Accepted for oral presentation at the 7th Workshop on Argument Mining (ARGMIN 2020) held at The 28th International Conference on Computational Linguistics (COLING 2020)[38] CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection作者 | Severin Laicher, Gioia Baldissin, Enrique Castañeda, Dominik Schlechtweg, Sabine Schulte im Walde連結 | https://arxiv.org/abs/2011.07247 [39] Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection作者 | Md Tahmid Rahman Laskar, Enamul Hoque, Jimmy Xiangji Huang連結 | https://arxiv.org/abs/2011.07208 備註 | Accepted to the AMMCS 2019 Proceedings[40] Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling作者 | Shruti Bhosale, Kyra Yee, Sergey Edunov, Michael Auli連結 | https://arxiv.org/abs/2011.07164 備註 | Accepted at WMT 2020[41] IIRC: A Dataset of Incomplete Information Reading Comprehension Questions作者 | James Ferguson, Matt Gardner, Hannaneh Hajishirzi, Tushar Khot, Pradeep Dasigi連結 | https://arxiv.org/abs/2011.07127 [42] Zero-shot Learning for Relation Extraction作者 | Jiaying Gong, Hoda Eldardiry連結 | https://arxiv.org/abs/2011.07126 備註 | 11 pages, 7 figures, submitted to WWW 2021[43] Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition作者 | Ching-Feng Yeh, Yongqiang Wang, Yangyang Shi, Chunyang Wu, Frank Zhang, Julian Chan, Michael L. Seltzer連結 | https://arxiv.org/abs/2011.07120 備註 | IEEE Spoken Language Technology Workshop 2021[44] The Teacher-Student Chatroom Corpus作者 | Andrew Caines, Helen Yannakoudakis, Helena Edmondson, Helen Allen, Pascual Pérez-Paredes, Bill Byrne, Paula Buttery連結 | https://arxiv.org/abs/2011.07109 [45] Sampling Approach Matters: Active Learning for Robotic Language Acquisition作者 | Nisha Pillai, Edward Raff, Francis Ferraro, Cynthia Matuszek連結 | https://arxiv.org/abs/2011.08021 備註 | To appear in IEEE Big Data 2020[46] Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets作者 | Rahul Yedida, Saad Mohammad Abrar, Cleber Melo-Filho, Eugene Muratov, Rada Chirkova, Alexander Tropsha連結 | https://arxiv.org/abs/2011.07959 [47] hyper-sinh: An Accurate and Reliable Function from Shallow to Deep Learning in TensorFlow and Keras作者 | Luca Parisi, Renfei Ma, Narrendar RaviChandran, Matteo Lanzillotta連結 | https://arxiv.org/abs/2011.07661 備註 | 19 pages, 6 listings/Python code snippets, 4 figures, 5 tables[48] Deep multi-modal networks for book genre classification based on its cover作者 | Chandra Kundu, Lukun Zheng連結 | https://arxiv.org/abs/2011.07658 [49] Generating Negative Commonsense Knowledge作者 | Tara Safavi, Danai Koutra連結 | https://arxiv.org/abs/2011.07497 備註 | Preprint, ongoing work[50] Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following作者 | Valts Blukis, Ross A. Knepper, Yoav Artzi連結 | https://arxiv.org/abs/2011.07384 備註 | 4th Conference on Robot Learning (CoRL 2020), Cambridge MA, USA