The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these problems we propose a novel source-side token prediction module. Our method jointly estimates the probability distributions over source and target vocabularies to capture a correspondence between source and target tokens. The experiments show that the proposed model outperforms the current state-of-the-art method in the headline generation task. Additionally, we show that our method has an ability to learn a reasonable token-wise correspondence without knowing any true alignments.
State Key Laboratory of Intelligent Technology and Systems(智能技术与系统国家重点实验室);Tsinghua National Laboratory for Information Science and Technology(清华信息科学与技术国家实验室);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)
A Large-Scale Multi-Length Headline Corpus for Analyzing Length-Constrained Headline Generation Model Evaluation
The Asahi Shimbun Company(朝日新闻社);Retrieva, Inc.(Retrieva公司);Tokyo Institute of Technology(东京工业大学);Tohoku University(东北大学);RIKEN Center Advanced Intelligence Project(理化学研究所先进智能项目中心)
Nagoya University(名古屋大学);Insight Edge, Inc.(Insight Edge 公司);The Asahi Shimbun Company(朝日新闻社);Tokyo Institute of Technology(东京工业大学);Tohoku University(东北大学);RIKEN AIP(理化学研究所革新智能综合研究中心)
CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China
Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE(教育部民族语言智能分析与安全治理重点实验室);Minzu University of China(民族大学);Shanghai Jiao Tong University(上海交通大学)
When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation
Charles Sturt University(查尔斯斯特大学);Chittagong University of Engineering and Technology(吉大港工程技术大学);Bangladesh Army University of Science and Technology(孟加拉国陆军理工大学)
Vārta: A Large-Scale Headline-Generation Dataset for Indic Languages
Mila – Quebec Artificial Intelligence Institute(米拉-魁北克人工智能研究所);McGill University(麦吉尔大学);IIT Madras(印度理工学院马德拉斯分校);AI4Bharat(AI4Bharat(印度人工智能研究机构));CIFAR AI Chair(加拿大高等研究院人工智能讲席)
Automatic Generation of Headlines for Online Math Questions
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);The Pennsylvania State University(宾夕法尼亚州立大学);School of Data and Computer Science, Sun Yat-sen University(中山大学数据科学与计算机学院)
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS(中国科学院计算技术研究所智能信息处理重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Institute of Intelligent Computing Technology, Suzhou, CAS(中国科学院苏州智能计算技术研究院)
RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation
National University of Science and Technology POLITEHNICA Bucharest(布加勒斯特理工国立科学技术大学);National Institute for Research and Development in Informatics - ICI Bucharest(布加勒斯特国家信息学研究与发展研究所);Paris 1 Panthéon-Sorbonne University(巴黎第一大学先贤祠-索邦大学);University of Bucharest(布加勒斯特大学)
Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback
Henan Institute of Advanced Technology, Zhengzhou University(河南高级技术研究所,郑州大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Independent Researcher(独立研究者)
BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion
Chittagong University of Engineering and Technology(吉大港工程技术大学);Bangladesh Army University of Science and Technology (BAUST)(孟加拉国陆军科技大学);Charles Sturt University(查尔斯斯特大学)
MOPO: Multi-Objective Prompt Optimization for Affective Text Generation
Institut für Maschinelle Sprachverarbeitung, University of Stuttgart(斯图加特大学机器语言研究所);Fundamentals of Natural Language Processing, University of Bamberg(班贝格大学自然语言处理基础研究所)
LLM-guided headline rewriting for clickability enhancement without clickbait
Intelligent Systems, Afeka Academic College of Engineering(阿菲卡工程学院智能系统系);School of Computer Science, Faculty of Sciences, HIT-Holon Institute of Technology(霍隆理工学院理学院计算机科学系)
COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation
Department of Computer Science and Engineering, Indian Institute of Technology Patna, India(印度理工学院帕纳分校计算机科学与工程系);Department of Metallurgical and Materials Engineering, National Institute of Technology Tiruchirappalli, India(印度理工学院 Tiruchirappalli 金属与材料工程系);Department of Computer Science and Information Systems, BITS Pilani – Goa Campus, India(比斯·帕尼学院 Goa 分校计算机科学与信息系统系);Department of Computer Science and Engineering, Indian Institute of Information Technology Vadodara, India(印度信息科技学院瓦达拉分校计算机科学与工程系);Department of Computer Science and Engineering, B.M.S. College of Engineering, Bangalore, India(班加罗尔 B.M.S. 工程学院计算机科学与工程系);Université de Toulouse, IRIT UMR 5505 CNRS, France(图卢兹大学 IRIT UMR 5505 CNRS 实验室)
XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags
Ahsanullah University of Science & Technology(阿萨努拉科技大学);University of Alberta(阿尔伯塔大学);Université de Sherbrooke(谢布鲁克大学);Salesforce Research(Salesforce研究院);Nanyang Technological University(南洋理工大学)
IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages
IIT Madras(印度理工学院马德拉斯分校);Columbia University(哥伦比亚大学);National Institute of Information and Communications Technology(信息通信研究机构);Microsoft(微软);University of Edinburgh(爱丁堡大学);AI4Bharat