首页 > 其他分享 >神经网络问答生成最全模型、策略、应用相关论文、资源、评测整理分享

神经网络问答生成最全模型、策略、应用相关论文、资源、评测整理分享

时间:2023-06-23 10:33:39浏览次数:39  
标签:Wang Generation 最全 Question 神经网络 2019 2018 Questions 问答


神经网络问答生成最全模型、策略、应用相关论文、资源、评测整理分享_Self

    本文整理了基于神经网络的问答系统中,文本生成相关各种算法、优化策略、应用场景的经典论文,以及相关的评估、开源资源等等,需要朋友自取。

    资源整理自网络,源地址:https://github.com/teacherpeterpan/Question-Generation-Paper-List

 

目录

神经网络问答生成最全模型、策略、应用相关论文、资源、评测整理分享_Self_02

    

综述论文

    1.Recent Advances in Neural Question Generation. arxiv, 2018. 

    Liangming Pan, Wenqiang Lei, Tat-Seng Chua, Min-Yen Kan.

    

模型部分

    

基础Seq2Seq模型

    基于Attention机制的序列搭到序列的问题生成模型。

    1.Learning to ask: Neural question generation for reading comprehension. ACL, 2017. 

    Xinya Du, Junru Shao, Claire Cardie.

    2.Neural question generation from text: A preliminary study. NLPCC, 2017. 

    Qingyu Zhou, Nan Yang, Furu Wei, Chuanqi Tan, Hangbo Bao, Ming Zhou.

    3.Machine comprehension by text-to-text neural question generation. Rep4NLP@ACL, 2017. 

    Xingdi Yuan, Tong Wang, Çaglar Gülçehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, Adam Trischler

    

问题编码

    用于对答案进行编码,以获取更好的问题-答案对应关系的技术。

    1.Answer-focused and Position-aware Neural Question Generation. EMNLP, 2018. 

    Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

    2.Improving Neural Question Generation Using Answer Separation. AAAI, 2019.  code

    Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung.

    3.Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring. AAAI, 2020. 

    Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu

    

语言学特征

    通过在QG过程中引入语言学特征提升QG的质量。

    1.Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features. INLG, 2018. 

    Vrindavan Harrison, Marilyn Walker

    2.Automatic Question Generation using Relative Pronouns and Adverbs. ACL, 2018. 

    Payal Khullar, Konigari Rachna, Mukul Hase, Manish Shrivastava

    3.Learning to Generate Questions by Learning What not to Generate. WWW, 2019.  code

    Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.

    4.Improving Neural Question Generation using World Knowledge. arXiv, 2019. 

    Deepak Gupta, Kaheer Suleman, Mahmoud Adada, Andrew McNamara, Justin Harris

    

问题相关的Reward

    引入强化学习,通过最大化特定的Reward来优化模型训练。

    1.Teaching Machines to Ask Questions. IJCAI, 2018. 

    Kaichun Yao, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu

    2.Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation arxiv, 2019. 

    Yu Chen, Lingfei Wu, Mohammed J. Zaki

    3.Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model NeurIPS Workshop, 2019. 

    Yu Chen, Lingfei Wu, Mohammed J. Zaki

    4.Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text CoNLL, 2019. 

    Vishwajeet Kumar, Ganesh Ramakrishnan, Yuan-Fang Li

    5.Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering EMNLP, 2019. code

    Shiyue Zhang, Mohit Bansal

    

内容选择

    通过选择与答案最相关的内容来优化QG质量。

    1.Identifying Where to Focus in Reading Comprehension for Neural Question Generation. EMNLP, 2017. 

    Xinya Du, Claire Cardie

    2.Answer-based Adversarial Training for Generating Clarification Questions. NAACL, 2019.  code

    Rao S, Daumé III H.

    3.Learning to Generate Questions by Learning What not to Generate. WWW, 2019.  code

    Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu.

    4.Improving Question Generation With to the Point Context. EMNLP, 2019. 

    Jingjing Li, Yifan Gao, Lidong Bing, Irwin King, Michael R. Lyu.

    5.Weak Supervision Enhanced Generative Network for Question Generation. IJCAI, 2019. 

    Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao, Jun Xiao, Yueting Zhuang

    6.A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation. AAAI, 2019. 

    Siyuan Wang, Zhongyu Wei, Zhihao Fan, Yang Liu, Xuanjing Huang

    

问题类型建模

    通过特定的词对QG的问题继续分类,以优化QG。

    1.Question Generation for Question Answering. EMNLP,2017. 

    Nan Duan, Duyu Tang, Peng Chen, Ming Zhou

    2.Answer-focused and Position-aware Neural Question Generation. EMNLP, 2018. 

    Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang

    3.Let Me Know What to Ask: Interrogative-Word-Aware Question Generation EMNLP Workshop, 2019. 

    Junmo Kang, Haritz Puerto San Roman, Sung-Hyon Myaeng

    4.Question-type Driven Question Generation EMNLP, 2019. 

    Wenjie Zhou, Minghua Zhang, Yunfang Wu

    

编码上下文信息

    引入输入文章的上下文信息来优化QG。

    1.Harvesting paragraph-level question-answer pairs from wikipedia. ACL, 2018.  code&dataset

    Xinya Du, Claire Cardie

    2.Leveraging Context Information for Natural Question Generation ACL, 2018.  code

    Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea

    3.Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks. EMNLP, 2018. 

    Yao Zhao, Xiaochuan Ni, Yuanyuan Ding, Qifa Ke

    4.Capturing Greater Context for Question Generation arxiv, 2019. 

    Luu Anh Tuan, Darsh J Shah, Regina Barzilay

    

其他方法

    1.Cross-Lingual Training for Automatic Question Generation. ACL, 2019.  dataset

    Vishwajeet Kumar, Nitish Joshi, Arijit Mukherjee, Ganesh Ramakrishnan, Preethi Jyothi

    2.Generating Question-Answer Hierarchies. ACL, 2019.  code

    Kalpesh Krishna and Mohit Iyyer.

    3.Unified Language Model Pre-training for Natural Language Understanding and Generation. NeurIPS, 2019. code

    Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon

    4.Can You Unpack That? Learning to Rewrite Questions-in-Context. EMNLP, 2019. 

    Ahmed Elgohary, Denis Peskov, Jordan L. Boyd-Graber

    5.Sequential Copying Networks. AAAI, 2018. 

    Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou

    

应用相关

    

可控QG的问题

    解决问题答案生成过程中人工干预的存在问题。

    1.Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation. arxiv, 2019. 

    Jie Zhao, Xiang Deng, Huan Sun.

    2.Difficulty Controllable Generation of Reading Comprehension Questions. IJCAI, 2019. 

    Yifan Gao, Lidong Bing, Wang Chen, Michael R. Lyu, Irwin King

    3.Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs. ISWC, 2019.  code&dataset

    Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li

    

对话系统中QG

    对话系统中,多轮对话中如何生成连贯的问题答案。

    1.Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders. ACL, 2018.  codedataset

    Yansen Wang, Chenyi Liu, Minlie Huang, Liqiang Nie

    2.Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling. ACL, 2019. code

    Yifan Gao, Piji Li, Irwin King, Michael R. Lyu

    3.Reinforced Dynamic Reasoning for Conversational Question Generation. ACL, 2019.  code dataset

    Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun

    4.Towards Answer-unaware Conversational Question Generation. ACL Workshop, 2019. 

    Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi

    

询问特定问题

    探索如何生成特定的类型的问题,比如数学问题,开放性问题,非事实性问题,阐述性问题。

    1.Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions. ACL Workshop, 2017. 

    Sudha Rao

    2.Automatic Opinion Question Generation. ICNLG, 2018. 

    Yllias Chali, Tina Baghaee

    3.A Multi-language Platform for Generating Algebraic Mathematical Word Problems. arxiv, 2019. 

    Vijini Liyanage, Surangika Ranathunga

    4.Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums. ACL, 2019. 

    Zi Chai, Xinyu Xing, Xiaojun Wan, Bo Huang

    5.Conclusion-Supplement Answer Generation for Non-Factoid Questions. AAAI, 2020. 

    Makoto Nakatsuji, Sohei Okui

    6.Answer-based Adversarial Training for Generating Clarification Questions. NAACL, 2019.  code

    Rao S, Daumé III H.

    7.Distant Supervised Why-Question Generation with Passage Self-Matching Attention. IJCNN, 2019. 

    Jiaxin Hu, Zhixu Li, Renshou Wu, Hongling Wang, An Liu, Jiajie Xu, Pengpeng Zhao, Lei Zhao


答案无关QG

    在答案无关的QG中,模型需要将问题无关的答案当作回答的主旨。因此,模型需要自动判断问题答案是否在文章当中。

    1.Learning to ask: Neural question generation for reading comprehension. ACL, 2017. 

    Xinya Du, Junru Shao, Claire Cardie.

    2.Neural Models for Key Phrase Extraction and Question Generation. ACL Workshop, 2018. 

    Sandeep Subramanian, Tong Wang, Xingdi Yuan, Saizheng Zhang, Adam Trischler, Yoshua Bengio

    3.Self-Attention Architectures for Answer-Agnostic Neural Question Generation. ACL, 2019. 

    Thomas Scialom, Benjamin Piwowarski, Jacopo Staiano.

    

无答案QG

    处理基于输入文章无法生成答案的问题。

    1.Learning to Ask Unanswerable Questions for Machine Reading Comprehension. ACL, 2019. 

    Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

    

组合QA和QG

    通过联合或多任务学习将QA和QG联合学习。

    1.Question Generation for Question Answering. EMNLP,2017. 

    Nan Duan, Duyu Tang, Peng Chen, Ming Zhou

    2.Learning to Collaborate for Question Answering and Asking. NAACL, 2018. 

    Duyu Tang, Nan Duan, Zhao Yan, Zhirui Zhang, Yibo Sun, Shujie Liu, Yuanhua Lv, Ming Zhou

    3.Generating Highly Relevant Questions. EMNLP, 2019. 

    Jiazuo Qiu, Deyi Xiong

    4.Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds. arxiv, 2019. 

    Tassilo Klein, Moin Nabi

    5.Triple-Joint Modeling for Question Generation Using Cross-Task Autoencoder. NLPCC, 2019. 

    Hongling Wang, Renshou Wu, Zhixu Li, Zhongqing Wang, Zhigang Chen, Guodong Zhou

    6.Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering EMNLP, 2019. code

    Shiyue Zhang, Mohit Bansal

    

基于知识图谱的QG

    将知识图谱引用与QG中技术。

    1.Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. ACL, 2016.  dataset

    Iulian Vlad Serban, Alberto García-Durán, Çaglar Gülçehre, Sungjin Ahn, Sarath Chandar, Aaron C. Courville, Yoshua Bengio

    2.Generating Natural Language Question-Answer Pairs from a Knowledge Graph Using a RNN Based Question Generation Model. ACL, 2017. 

    Mitesh M. Khapra, Dinesh Raghu, Sachindra Joshi, Sathish Reddy

    3.Knowledge Questions from Knowledge Graphs. ICTIR, 2017. 

    Dominic Seyler, Mohamed Yahya, Klaus Berberich.

    4.Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types. NAACL, 2018. code

    Hady Elsahar, Christophe Gravier, Frederique Laforest.

    5.A Neural Question Generation System Based on Knowledge Base NLPCC, 2018. 

    Hao Wang, Xiaodong Zhang, Houfeng Wang

    6.Formal Query Generation for Question Answering over Knowledge Bases. ESWC, 2018. 

    Hamid Zafar, Giulio Napolitano, Jens Lehmann

    7.Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss. EMNLP, 2019. 

    Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao

    8.Difficulty-controllable Multi-hop Question Generation From Knowledge Graphs. ISWC, 2019.  code&dataset

    Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan-Fang Li

    9.How Question Generation Can Help Question Answering over Knowledge Base. NLPCC, 2019. 

    Sen Hu, Lei Zou, Zhanxing Zhu

    

可视化问题答案生成

    通过一张输入图片生成答案。

    1.Generating Natural Questions About an Image ACL, 2016. 

    Nasrin Mostafazadeh, Ishan Misra, Jacob Devlin, Margaret Mitchell, Xiaodong He, Lucy Vanderwende

    2.Creativity: Generating Diverse Questions Using Variational Autoencoders CVPR,2017. 

    Unnat Jain, Ziyu Zhang, Alexander G. Schwing

    3.Automatic Generation of Grounded Visual Questions IJCAI, 2017. 

    Shijie Zhang, Lizhen Qu, Shaodi You, Zhenglu Yang, Jiawan Zhang

    4.A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators COLING, 2018. 

    Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang

    5.Customized Image Narrative Generation via Interactive Visual Question Generation and Answering CVPR, 2018. 

    Andrew Shin, Yoshitaka Ushiku, Tatsuya Harada

    6.Multimodal Differential Network for Visual Question Generation EMNLP, 2018. 

    Badri Narayana Patro, Sandeep Kumar, Vinod Kumar Kurmi, Vinay P. Namboodiri

    7.A Question Type Driven Framework to Diversify Visual Question Generation IJCAI, 2018. 

    Zhihao Fan, Zhongyu Wei, Piji Li, Yanyan Lan, Xuanjing Huang

    8.Visual Question Generation as Dual Task of Visual Question Answering. CVPR, 2018. 

    Yikang Li, Nan Duan, Bolei Zhou, Xiao Chu, Wanli Ouyang, Xiaogang Wang, Ming Zhou

    9.Information Maximizing Visual Question Generation. CVPR, 2019. 

    Ranjay Krishna, Michael Bernstein, Li Fei-Fei

    

误导性QG

    学习从多个候选问题生成答案。

    1.Generating Questions and Multiple-Choice Answers using Semantic Analysis of Texts. COLING, 2016. 

    Jun Araki, Dheeraj Rajagopal, Sreecharan Sankaranarayanan, Susan Holm, Yukari Yamakawa, Teruko Mitamura

    2.Distractor Generation for Multiple Choice Questions Using Learning to Rank. NAACL Workshop, 2018.  code

    Chen Liang, Xiao Yang, Neisarg Dave, Drew Wham, Bart Pursel, C. Lee Giles

    3.Generating Distractors for Reading Comprehension Questions from Real Examinations. AAAI, 2019. 

    Yifan Gao, Lidong Bing, Piji Li, Irwin King, Michael R. Lyu

    

评估

    问答系统中一个子方向,评估QG生成的质量。

    1.Question Asking as Program Generation. NeurIPS, 2017. 

    Anselm Rothe, Brenden M. Lake, Todd M. Gureckis.

    2.Towards a Better Metric for Evaluating Question Generation Systems. EMNLP, 2018. 

    Preksha Nema, Mitesh M. Khapra.

    3.LearningQ: A Large-Scale Dataset for Educational Question Generation. ICWSM, 2018. 

    Guanliang Chen, Jie Yang, Claudia Hauff, Geert-Jan Houben.

    4.Evaluating Rewards for Question Generation Models. NAACL, 2019. 

    Tom Hosking and Sebastian Riedel.

   

相关资源

    QG相关的数据集和工具。

    1.ParaQG: A System for Generating Questions and Answers from Paragraphs. EMNLP Demo, 2019. 

    Vishwajeet Kumar, Sivaanandh Muneeswaran, Ganesh Ramakrishnan, Yuan-Fang Li.

    2.How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions. AAAI, 2020.  code

    Zewei Chu, Mingda Chen, Jing Chen, Miaosen Wang, Kevin Gimpel, Manaal Faruqui, Xiance Si.

标签:Wang,Generation,最全,Question,神经网络,2019,2018,Questions,问答
From: https://blog.51cto.com/u_13046751/6537327

相关文章

  • 历史最全图像/视频去模糊化精选论文整理分享
        本资源整理了图像/视频图模糊化相关的经典论文、相关的数据集。涉及基于深度学习技术的单图像盲运动去模糊化,非深度学习单图像盲运动去模糊化,非盲去模糊化,多图像/视频运动去模糊化等方面,分享给需要的朋友。     资源整理自网络,源地址:https://github.com/subeeshvasu/......
  • 神经网络第二周
    Classicnetworks:LeNet-5,针对灰度图像训练的AlexNetVGG(VGG-16,16表示的是包含16个卷积层和全连接层;卷积层后面跟着可以压缩图像大小的池化层,池化层缩小图像的高度和宽度)ResNet(残差网络)ResNetws是由残差块构建的 看过程在残差网络中,我们将a[l]直接向后,拷贝到神经网......
  • 历史最全GAN模型PyTorch代码实现整理分享
        如果你是第一次接触AE自编码器和GAN生成对抗网络,那这将会是一个非常有用且效率的学习资源。所有的内容使用PyTorch编写,编写格式清晰,非常适合PyTorch新手作为学习资源。本项目的所有模型目前都是基于MNIST数据库进行图片生成。MNIST数据集是一个比较小,一个光CPU就能跑起来的......
  • 历史最全Java资源大全中文版整理分享
       很多程序员应该记得GitHub上有一个Awesome-XXX系列的资源整理。本资源对Java相关的资源列表进行翻译和整理,内容包括:构建工具、数据库、框架、模板、安全、代码分析、日志、第三方库、书籍、Java站点等。分享给需要的朋友。目录内容截图......
  • 吴恩达卷积神经网络
    过滤器、padding(6)、卷积步长(7)、三维卷积、池化层神经网络的前几层如何检测边缘,有些后面的层可能检测到物体的部分,更靠后的一些层,可能检测到完整的物体eg:给一个例子,可能首先检测图片中的垂直边缘,或者那你想检测水平边缘这是6*6*1的灰度矩阵,不是6*6*3的,因为没有RGB三通道。可......
  • 蔬菜识别系统Python+TensorFlow+Django+卷积神经网络算法
    一、介绍蔬菜识别系统,使用Python作为主要开发语言,基于深度学习TensorFlow框架,搭建卷积神经网络算法。并通过对数据集进行训练,最后得到一个识别精度较高的模型。并基于Django框架,开发网页端操作平台,实现用户上传一张图片识别其名称。二、效果图片三、演示视频+代码视频+完整......
  • 鸟类识别系统Python+Django+TensorFlow+卷积神经网络算法【完整代码】
    一、介绍鸟类识别系统,使用Python作为主要开发语言,基于深度学习TensorFlow框架,搭建卷积神经网络算法。并通过对数据集进行训练,最后得到一个识别精度较高的模型。并基于Django框架,开发网页端操作平台,实现用户上传一张图片识别其名称。数据集选自加州理工学院200种鸟类数据集二、......
  • 史上最全Android性能优化方案解析
    Android中的性能优分为以下几个方面:布局优化网络优化安装包优化内存优化卡顿优化启动优化……一.布局优化布局优化的本质就是减少View的层级。常见的布局优化方案如下:在LinearLayout和RelativeLayout都可以完成布局的情况下优先选择LinearLayout,可以减少View的层级,但是注意相同组......
  • 蔬菜识别系统Python+TensorFlow+Django+卷积神经网络算法
    一、介绍蔬菜识别系统,使用Python作为主要开发语言,基于深度学习TensorFlow框架,搭建卷积神经网络算法。并通过对数据集进行训练,最后得到一个识别精度较高的模型。并基于Django框架,开发网页端操作平台,实现用户上传一张图片识别其名称。二、效果图片三、演示视频+代码视频+完整代码:http......
  • 手写数字识别系统Python+CNN卷积神经网络算法【完整代码】
    一、介绍手写数字识别系统,使用Python语言,基于TensorFlow搭建CNN卷积神经网络算法对数据集进行训练,最后得到模型,并基于FLask搭建网页端界面,基于Pyqt5搭建桌面端可视化界面。二、效果展示三、演示视频+完整代码视频+代码:https://www.yuque.com/ziwu/yygu3z/tb1mzqi847daqkru......