出品 | 深度学习这件小事公众号
自然语言处理(12月15日更新版)
[1] Massive-scale Decoding for Text Generation using Lattices作者 | Jiacheng Xu, Greg Durrett链接 | https://arxiv.org/abs/2112.07660 项目链接 | https://github.com/jiacheng-xu/lattice-generation[2] On the Use of External Data for Spoken Named Entity Recognition作者 | Ankita Pasad, Felix Wu, Suwon Shon, Karen Livescu, Kyu J. Han链接 | https://arxiv.org/abs/2112.07648 [3] Exploring Neural Models for Query-Focused Summarization作者 | Jesse Vig, Alexander R. Fabbri, Wojciech Kryściński链接 | https://arxiv.org/abs/2112.07637 [4] Improving Compositional Generalization with Latent Structure and Data Augmentation作者 | Linlu Qiu, Peter Shaw, Panupong Pasupat, Paweł Krzysztof Nowak, Tal Linzen, Fei Sha, Kristina Toutanova链接 | https://arxiv.org/abs/2112.07610 [5] Semantic Answer Type and Relation Prediction Task (SMART 2021)作者 | Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo, Jens Lehmann, Axel-Cyrille Ngonga Ngomo, Ricardo Usbeck, Gaetano Rossiello, Uttam Kumar链接 | https://arxiv.org/abs/2112.07606 [6] The King is Naked: on the Notion of Robustness for Natural Language Processing作者 | Emanuele La Malfa, Marta Kwiatkowska链接 | https://arxiv.org/abs/2112.07605 备注 | AAAI 2022 main-track (full-paper)[7] Reinforcing Semantic-Symmetry for Document Summarization作者 | Mingyang Song, Liping Jing链接 | https://arxiv.org/abs/2112.07583 [8] GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval作者 | Kexin Wang, Nandan Thakur, Nils Reimers, Iryna Gurevych链接 | https://arxiv.org/abs/2112.07577 [9] VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena作者 | Letitia Parcalabescu, Michele Cafagna, Lilitta Muradjan, Anette Frank, Iacer Calixto, Albert Gatt链接 | https://arxiv.org/abs/2112.07566 备注 | 28 pages, 4 figures, 11 tables[10] Scaling Up Query-Focused Summarization to Meet Open-Domain Question Answering作者 | Weijia Zhang, Svitlana Vakulenko, Thilina Rajapakse, Evangelos Kanoulas链接 | https://arxiv.org/abs/2112.07536 [11] Reinforced Abstractive Summarization with Adaptive Length Controlling作者 | Mingyang Song, Yi Feng, Liping Jing链接 | https://arxiv.org/abs/2112.07534 [12] LMTurk: Few-Shot Learners as Crowdsourcing Workers作者 | Mengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li, Xin Jiang, Qun Liu, Hinrich Schütze链接 | https://arxiv.org/abs/2112.07522 [13] Sentiment Dynamics of Success: Fractal Scaling of Story Arcs Predicts Reader Preferences作者 | Yuri Bizzoni, Telma Peura, Mads R. Thomsen, Kristoffer Nielbo链接 | https://arxiv.org/abs/2112.07497 [14] Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks作者 | Paul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert链接 | https://arxiv.org/abs/2112.07475 [15] Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models作者 | Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, Bettina Berendt链接 | https://arxiv.org/abs/2112.07447 备注 | 15 pages, 4 figures, 3 tables[16] Text Classification Models for Form Entity Linking作者 | María Villota, César Domínguez, Jónathan Heras, Eloy Mata, Vico Pascual链接 | https://arxiv.org/abs/2112.07443 [17] Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detection作者 | Vijit Malik, Ayush Kumar, Jithendra Veppa链接 | https://arxiv.org/abs/2112.07434 [18] Towards A Reliable Ground-Truth For Biased Language Detection作者 | Timo Spinde, David Krieger, Manuel Plank, Bela Gipp链接 | https://arxiv.org/abs/2112.07421 [19] Do You Think It's Biased? How To Ask For The Perception Of Media Bias作者 | Timo Spinde, Christina Kreuter, Wolfgang Gaissmaier, Felix Hamborg, Bela Gipp, Helge Giese链接 | https://arxiv.org/abs/2112.07392 [20] TASSY -- A Text Annotation Survey System作者 | Timo Spinde, Kanishka Sinha, Norman Meuschke, Bela Gipp链接 | https://arxiv.org/abs/2112.07391 [21] Identification of Biased Terms in News Articles by Comparison of Outlet-specific Word Embeddings作者 | Timo Spinde, Lada Rudnitckaia, Felix Hamborg, Bela Gipp链接 | https://arxiv.org/abs/2112.07384 [22] You Only Need One Model for Open-domain Question Answering作者 | Haejun Lee, Akhil Kedia, Jongwon Lee, Ashwin Paranjape, Christopher D. Manning, Kyoung-Gu Woo链接 | https://arxiv.org/abs/2112.07381 [23] Multi-Instance Training for Question Answering Across Table and Linked Text作者 | Vishwajeet Kumar, Saneem Chemmengath, Yash Gupta, Jaydeep Sen, Samarth Bharadwaj, Soumen Chakrabarti链接 | https://arxiv.org/abs/2112.07337 [24] Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models作者 | Lei Li, Yankai Lin, Xuancheng Ren, Guangxiang Zhao, Peng Li, Jie Zhou, Xu Sun链接 | https://arxiv.org/abs/2112.07327 [25] Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrieval作者 | Yosi Mass, Doron Cohen, Asaf Yehudai, David Konopnicki链接 | https://arxiv.org/abs/2112.07308 [26] Simple Local Attentions Remain Competitive for Long-Context Tasks作者 | Wenhan Xiong, Barlas Oğuz, Anchit Gupta, Xilun Chen, Diana Liskovich, Omer Levy, Wen-tau Yih, Yashar Mehdad链接 | https://arxiv.org/abs/2112.07210 [27] From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression作者 | Runxin Xu, Fuli Luo, Chengyu Wang, Baobao Chang, Jun Huang, Songfang Huang, Fei Huang链接 | https://arxiv.org/abs/2112.07198 备注 | Accepted to AAAI 2022[28] MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation作者 | Chen Zhang, Luis Fernando D'Haro, Thomas Friedrichs, Haizhou Li链接 | https://arxiv.org/abs/2112.07194 备注 | Accepted to AAAI2022 (10 pages, 3 figures, Preprint version)[29] Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models作者 | Jaromir Savelka, Kevin D. Ashley链接 | https://arxiv.org/abs/2112.07165 [30] Building on Huang et al. GlossBERT for Word Sense Disambiguation作者 | Nikhil Patel, James Hale, Kanika Jindal, Apoorva Sharma, Yichun Yu链接 | https://arxiv.org/abs/2112.07089 [31] Language Models are not Models of Language链接 | https://arxiv.org/abs/2112.07055 [32] Framework para Caracterizar Fake News en Terminos de Emociones作者 | Luis Rojas Rubio, Claudio Meneses Villegas链接 | https://arxiv.org/abs/2112.07035 [33] Event Based Time-Vectors for auditory features extraction: a neuromorphic approach for low power audio recognition作者 | Marco Rasetto, Juan P. Dominguez-Morales, Angel Jimenez-Fernandez, Ryad Benosman链接 | https://arxiv.org/abs/2112.07011 [34] Controlled Cue Generation for Play Scripts作者 | Alara Dirik, Hilal Donmez, Pinar Yanardag链接 | https://arxiv.org/abs/2112.06953 [35] Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing作者 | Shailza Jolly, Pepa Atanasova, Isabelle Augenstein链接 | https://arxiv.org/abs/2112.06924 [36] Dual-Key Multimodal Backdoors for Visual Question Answering作者 | Matthew Walmer, Karan Sikka, Indranil Sur, Abhinav Shrivastava, Susmit Jha链接 | https://arxiv.org/abs/2112.07668 [37] ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs作者 | Manas Gaur, Kalpa Gunaratna, Vijay Srinivasan, Hongxia Jin链接 | https://arxiv.org/abs/2112.07622 项目链接 | https://github.com/manasgaur/AAAI-22备注 | Accepted at AAAI 2022, preprint version. [38] CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising作者 | Jianjie Luo, Yehao Li, Yingwei Pan, Ting Yao, Hongyang Chao, Tao Mei链接 | https://arxiv.org/abs/2112.07515 [39] TopNet: Learning from Neural Topic Model to Generate Long Stories作者 | Yazheng Yang, Boyuan Pan, Deng Cai, Huan Sun链接 | https://arxiv.org/abs/2112.07259 [40] Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model作者 | Keqi Deng, Songjun Cao, Yike Zhang, Long Ma链接 | https://arxiv.org/abs/2112.07254
扫描二维码添加小助手微信(ID : HIT_NLP)