Adaptive Parameterization for Neural Dialogue Generation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Data Science Lab, JD.com（京东数据科学实验室）
Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic responses. In this work, we propose an {\bf Ada}ptive {\bf N}eural {\bf D}ialogue generation model, \textsc{AdaND}, which manages various conversations with conversation-specific parameterization. For each conversation, the model generates parameters of the encoder-decoder by referring to the input context. In particular, we propose two adaptive parameterization mechanisms: a context-aware and a topic-aware parameterization mechanism. The context-aware parameterization directly generates the parameters by capturing local semantics of the given context. The topic-aware parameterization enables parameter sharing among conversations with similar topics by first inferring the latent topics of the given context and then generating the parameters with respect to the distributional topics. Extensive experiments conducted on a large-scale real-world conversational dataset show that our model achieves superior performance in terms of both quantitative metrics and human evaluations.
Dialogue-adaptive Language Model Pre-training From Quality Estimation
Shanghai Jiao Tong University（上海交通大学）
预训练语言模型（Pre-trained language models，PrLM）凭借其在大规模语料库上通过自监督学习获得的通用语言表示能力，在广泛的自然语言处理任务中取得了巨大的成功。这些模型是在具有一般语言模型（LM）训练目标的标准纯文本上预训练的，这将不足以对这些任务中反映的对话专有属性（如特异性和信息性）进行建模，这些对话专有属性未被预训练的通用语言表示明确捕获。在这项工作中，我们提出了对话自适应预训练目标（DAPO）来自质量估计模拟对话特定的功能，即连贯性，特异性和信息量。作为模型预训练的基础，我们合成了一个新的对话语料库，并使用两种无监督的方法来建立我们的训练集：1）面向连贯性的语境破坏，包括话语排序，插入和替换，以帮助模型捕获对话语境中的连贯性; 2）面向特异性的自动重评分，这鼓励模型通过考虑特异性和信息量来测量用于对话自适应预训练的合成数据的质量。在广泛使用的开放域响应选择和质量估计基准上的实验结果表明，DAPO显著改善了基线模型，并在Mutual排行榜上实现了最先进的性能，验证了将质量评估因素估计到预训练中的有效性。
Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Data Science Lab, JD.com（京东数据科学实验室）；National Computer network Emergency Response technical Team/Coordination Center of China（国家计算机网络应急技术处理协调中心）
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）；University of Adelaide（阿德莱德大学）
Personalized Dialogue Generation with Persona-Adaptive Attention
University of Surrey（萨里大学）；Southern University of Science and Technology（南方科技大学）；ByteDance AI Lab（字节跳动人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Adaptive Bridge between Training and Inference for Dialogue
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of AI Industry Research, Tsinghua University（清华大学智能产业研究院）
ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue
Zhejiang Normal University（浙江师范大学）；Alibaba Group（阿里巴巴集团）；Hong Kong University of Science and Technology（香港科学与技术大学）；Southeast University（东南大学）；Soochow University（苏州大学）
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Microsoft Research（微软研究院）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Carnegie Mellon University（卡内基梅隆大学）
UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
The Chinese University of Hong Kong（香港中文大学）；Nankai University（南开大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Seoul National University（首尔大学）；Columbia University（哥伦比亚大学）；University of California, Berkeley（加州大学伯克利分校）；Georgia Institute of Technology（佐治亚理工学院）
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
College of Design and Innovation, Tongji University（同济大学设计创意学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海自主智能无人系统科学中心）
SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training
McGill University（麦吉尔大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Institute of Health Sciences Education, McGill University（麦吉尔大学健康科学教育研究所）；School of Social Work, McGill University（麦吉尔大学社会工作学院）；Montreal Children’s Hospital, McGill University Health Centre（麦吉尔大学健康中心蒙特利尔儿童医院）；Steinberg Centre for Simulation and Interactive Learning, McGill University（麦吉尔大学斯坦伯格模拟与互动学习中心）；Linarite AI（利纳里特人工智能公司）
DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Beihang University（北京航空航天大学）；University of Chinese Academy of Sciences（中国科学院大学）；Codemao Inc.（编程猫公司）；University of Adelaide（阿德莱德大学）
Diversifying Dialog Generation via Adaptive Label Smoothing
Tsinghua University（清华大学）；Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Samsung Research China - Beijing (SRC-B)（三星电子中国研究院（北京））
PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
Indian Institute of Technology Patna（印度巴特那印度理工学院）；Ramakrishna Mission Vivekananda Educational and Research Institute（罗摩克里希纳使命维韦卡南达教育与研究学院）；Accenture Labs（埃森哲实验室）
