专栏名称: 深度学习这件小事
机器学习算法、深度学习算法、自然语言处理等干货知识集中营
目录
相关文章推荐
包头新闻网  ·  微信公告:下架 ·  2 天前  
包头新闻网  ·  微信公告:下架 ·  2 天前  
51好读  ›  专栏  ›  深度学习这件小事

每日论文速递:自然语言处理相关(12月15日更新版)

深度学习这件小事  · 公众号  ·  · 2021-12-15 17:05

正文

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(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 
备注 | 10 pages, 8 figures

[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 
备注 | 9 pages, 3 figures

[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 
备注 | preprint

[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 
备注 | 11 pages

[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
作者 | Csaba Veres
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 
备注 | in Spanish

[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 
备注 | 10 pages, 7 figures

[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 
备注 | ACM Multimedia 2021

[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 
备注 | KDD2021, 9 pages

[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 
备注 | ASRU2021


技术交流群邀请函



△长按添加小助手

扫描二维码添加小助手微信(ID : HIT_NLP

请备注:姓名-学校/公司-研究方向-城市
(如:小事-浙大-对话系统-北京)
即可申请加入深度学习/机器学习等技术交流群

为您推荐
每日论文速递:自然语言处理相关(12月14日版)
每日论文速递:自然语言处理相关(12月13日版)
每日论文速递:自然语言处理相关(12月10日版)
每日论文速递:自然语言处理相关(12月9日版)
每日论文速递:自然语言处理相关(12月8日版)

推荐文章
包头新闻网  ·  微信公告:下架
2 天前
包头新闻网  ·  微信公告:下架
2 天前
LOGO大师  ·  99%的人都被它骗了!
7 年前