检索结果-南通市图书馆

EVA2.0:Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2023年第2期20卷 207-219页

作者： Yuxian Gu Jiaxin Wen Hao Sun Yi Song Pei Ke Chujie Zheng Zheng Zhang Jianzhu Yao Lei Liu Xiaoyan Zhu minlie huang The Conversational AI Group Tsinghua UniversityBeijing 100084China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Department of Electrical Engineering and Computer Science York UniversityToronto M3J1P3Canada

Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.However,previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model,ignoring the discussion of some key factors towards a powerful human-like chatbot,especially in Chinese scenarios.In this paper,we conduct extensive experiments to investigate these under-explored factors,including data quality control,model architecture designs,training approaches,and decoding strategies.We propose EVA2.0,a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters,and will make our models and codes publicly available.Automatic and human evaluations show that EVA2.0 significantly outperforms other open-source counterparts.We also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems.

关键词： Natural language processing deep learning(DL) large-scale pre-training dialogue systems Chinese open-domain conversational model

Finding Nuggets in Patent Portfolios: Core Patent Mining and Its Applications

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2013年第4期18卷 339-352页

作者： Po Hu minlie huang Xiaoyan Zhu the Department of Computer Science and Technology Tsinghua University

Patents are critically important for a company to protect its core business concepts and proprietary technologies. Effective patent mining in massive patent databases not only provides business enterprises with valuable insights to develop strategies for research and development, intellectual property management, and product marketing, but also helps patent offices to improve efficiency and optimize their patent examination processes. This paper describes the patent mining problem of automatically discovering core patents （i.e., novel and influential patents in a domain）. In addition, the value of core patent mining is illustrated by revealing the potential competitive relationships among companies in their core patents. The work addresses the unique patent vocabulary usage which is not considered in traditional word-based statistical methods with a topic-based temporal mining approach that quantifies a patent＇s novelty and influence through topic activeness variations. Tests of this method on real-world patent portfolios show the effectiveness of this approach over state-of-the-art methods.

关键词： text mining core patent patent novelty patent influence company competitor

An Evaluation of Chinese Human-Computer Dialogue Technology

在线全文

学校读者我要写书评

暂无评论

Data Intelligence 2021年第2期3卷 274-286页

作者： Zixian Feng Caihai Zhu Weinan Zhang Zhigang Chen Wanxiang Che minlie huang Linlin Li Research Center for Social Computing and Information Retrieval Harbin Institute of TechnologyHarbin 150001China AI Research Institute IFLYTEK CO.LTD.Hefei 230088China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Consumer BG HUAWEI Technologies CO.LTD.Nanjing 210012China

There is a growing interest in developing human-computer dialogue systems which is an important branch in the field of artificial intelligence(AI).However,the evaluation of large-scale Chinese human-computer dialogues is still a challenging task.To attract more attention to dialogue evaluation work,we held the fourth Evaluation of Chinese Human-Computer Dialogue Technology(ECDT).It consists of few-shot learning in spoken language understanding(SLU)(Task 1)and knowledge-driven multi-turn dialogue competition(Task 2),the data sets of which are provided by Harbin Institute of Technology and Tsinghua University.In this paper,we will introduce the evaluation tasks and data sets in detail.Meanwhile,we will also analyze the evaluation results and the existing problems in the evaluation.

关键词： Chinese human-computer dialogue evaluation Evaluation data Few-shot learning Knowledge-driven multi-turn dialogue

Mining microblog user interests based on TextRank with TF-IDF factor

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2016年第5期23卷 40-46页

作者： Tu Shouzhong huang minlie State Key Laboratory of Intelligent Technology and Systems Tsinghua University

It is of great value and significance to model the interests of microblog user in terms of business and sociology. This paper presents a framework for mining and analyzing personal interests from microblog text with a new algorithm which integrates term frequency-inverse document frequency （TF-IDF） with TextRank. Firstly, we build a three-tier category system of user interest based on Wikipedia. In order to obtain the keywords of interest, we preprocess the posts, comments and reposts in different categories to select the keywords which appear both in the category system and microblogs. We then assign weight to each category and calculate the weight of keyword to get TF-IDF factors. Finally we score the ranking of each keyword by the TextRank algorithm with TF-IDF factors. Experiments on real Sina microblog data demonstrate that the precision of our approach significantly outperforms other existing methods.

关键词： microblog interest feature TF-IDF interest mining TextRank

Recent advances and challenges in task-oriented dialog systems

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2020年第10期63卷 2011-2027页

作者： ZHANG Zheng TAKANOBU Ryuichi ZHU Qi huang minlie ZHU XiaoYan Department of Computer Science&.Technology Tsinghua UniversityBeijing 100084China Institute for Artificial Intelligence Tsinghua University(THUAI)Beijing 100084China Beijing National Research Center for Information Science&Technology Beijing 100084China

Due to the significance and value in human-computer interaction and natural language processing,task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.In this paper,we survey recent advances and challenges in task-oriented dialog systems.We also discuss three critical topics for task-oriented dialog systems:(1)improving data efficiency to facilitate dialog modeling in low-resource settings,(2)modeling multi-turn dynamics for dialog policy learning to achieve better task-completion performance,and(3)integrating domain ontology knowledge into the dialog model.Besides,we review the recent progresses in dialog evaluation and some widely-used corpora.We believe that this survey,though incomplete,can shed a light on future research in task-oriented dialog systems.

关键词： task-oriented dialog systems natural language understanding dialog policy dialog state tracking natural language generation

以ChatGPT为代表的大型语言模型研究进展

在线全文

学校读者我要写书评

暂无评论

中国科学基金 2023年第5期37卷 714-723页

作者：柯沛雷文强黄民烈清华大学计算机科学与技术系四川大学计算机学院

大型语言模型是当今人工智能领域最前沿的研究方向之一，该方向旨在训练含有大规模参数的通用语言模型，使其能够遵循人类指令完成不同类型的自然语言处理任务。作为大型语言模型的代表，由OpenAI研发的ChatGPT在各个领域均展现出强大... 详细信息

大型语言模型是当今人工智能领域最前沿的研究方向之一，该方向旨在训练含有大规模参数的通用语言模型，使其能够遵循人类指令完成不同类型的自然语言处理任务。作为大型语言模型的代表，由OpenAI研发的ChatGPT在各个领域均展现出强大的自然语言生成能力，受到了全球各行各业的关注。本文从语言模型的发展历程出发，介绍了近年研究者在扩大语言模型规模上的探索，然后分析了大型语言模型带来的范式改变，并以ChatGPT为典型实例概述了其发展、技术和应用，接着介绍了后ChatGPT时代大型语言模型的前沿进展，最后从评价和治理两方面总结了目前大型语言模型的局限性及未来需要解决的挑战。

关键词：大型语言模型 ChatGPT 预训练语言模型 Transformer 思维链自然语言处理人工智能

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

一种半监督的中文垃圾微博过滤方法

中文信息学报 2016年第5期30卷 176-186页

作者：姚子瑜屠守中黄民烈朱小燕清华大学计算机科学与技术系北京100084

微博作为目前国内外最活跃的信息分享平台之一,其中却充斥着大量的垃圾内容。因此,如何从给定话题的微博数据中,过滤掉与话题不相关的垃圾微博、保留话题相关微博,成为迫切需要解决的问题。该文提出了一种半监督的中文微博过滤方法,基... 详细信息

微博作为目前国内外最活跃的信息分享平台之一,其中却充斥着大量的垃圾内容。因此,如何从给定话题的微博数据中,过滤掉与话题不相关的垃圾微博、保留话题相关微博,成为迫切需要解决的问题。该文提出了一种半监督的中文微博过滤方法,基于朴素贝叶斯分类模型和最大期望算法,实现了利用少量标注数据的垃圾微博过滤算法,其优势是仅仅利用少量标注数据就可以获得较为理想的过滤性能。分别对十个话题140 000余条新浪微博数据进行过滤,该文提出的模型准确度和F值优于朴素贝叶斯和支持向量机模型。

关键词：垃圾微博过滤半监督学习 EM算法朴素贝叶斯

大模型时代的自然语言处理:挑战、机遇与发展

在线全文

学校读者我要写书评

暂无评论

中国科学：信息科学 2023年第9期53卷 1645-1687页

作者：车万翔窦志成冯岩松桂韬韩先培户保田黄民烈黄萱菁刘康刘挺刘知远秦兵邱锡鹏万小军王宇轩文继荣严睿张家俊张民张奇赵军赵鑫赵妍妍北京大学王选计算机研究所北京100080 复旦大学计算机科学技术学院上海200438 复旦大学现代语言学研究院上海200433 哈尔滨工业大学计算学部哈尔滨150001 哈尔滨工业大学(深圳)计算机科学与技术学院深圳518055 清华大学计算机科学与技术系北京100084 苏州大学计算机科学与技术学院苏州215006 之江实验室杭州311121 中国科学院自动化研究所北京100190 中国科学院软件研究所北京100190 中国人民大学高人工智能学院北京100872

近期发布的ChatGPT和GPT-4等大型语言模型,不仅能高质量完成自然语言生成任务,生成流畅通顺,贴合人类需求的语言,而且具备以生成式框架完成各种开放域自然语言理解任务的能力.在少样本、零样本场景下,大模型可取得接近乃至达到传统监督... 详细信息

近期发布的ChatGPT和GPT-4等大型语言模型,不仅能高质量完成自然语言生成任务,生成流畅通顺,贴合人类需求的语言,而且具备以生成式框架完成各种开放域自然语言理解任务的能力.在少样本、零样本场景下,大模型可取得接近乃至达到传统监督学习方法的性能,且具有较强的领域泛化性,从而对传统自然语言核心任务产生了巨大的冲击和影响.本文就大模型对自然语言处理的影响进行了详细的调研和分析,试图探究大模型对自然语言处理核心任务带来哪些挑战和机遇,探讨大模型将加强哪些自然语言处理共性问题的研究热度,展望大模型和自然语言处理技术的未来发展趋势和应用.分析结果表明,大模型时代的自然语言处理依然大有可为.我们不仅可以将大模型作为研究方法和手段,学习、借鉴大型语言模型的特点和优势,变革自然语言处理的主流研究范式,对分散独立的自然语言处理任务进行整合,进一步提升自然语言核心任务的能力;还可就可解释性、公平性、安全性、信息准确性等共性问题开展深入研究,促进大模型能力和服务质量的提升.未来,以大模型作为基座,拓展其感知、计算、推理、交互和控制能力,自然语言处理技术将进一步助力通用人工智能的发展,促进各行各业的生产力进步,更好地为人类社会服务.

关键词： ChatGPT 对话式大模型大型语言模型自然语言处理通用人工智能

A new method for automatic pattern acquisition to extract information from biomedical texts

在线全文

学校读者我要写书评

暂无评论

A new method for automatic pattern acquisition to extract in...