A Persona-Based Neural Conversation Model论文学习零散记录
A Persona-Based Neural Conversation Model 这篇文章用来解决conversation model中的speaker consistency的问题。比方说，问chatbot“wh
7月前780
论文笔记：基于外部知识的会话模型A Knowledge-Grounded Neural Conversation Model
A Knowledge-Grounded Neural Conversation Model 1 出发点 现有的会话模型无法获得外部知识，网络产生的相应虽然在会话上恰当，但是包含的信息量很少 2 网络结构 图1：网络的整体结构 2.1 Di
7月前560
《论文阅读》PAL: Persona-Augmented Emotional Support Conversation Generation
《论文阅读》PAL: Persona-Augmented Emotional Support Conversation Generation 前言 简介 思路出发点 相关知识 coefficient of determination 任务定
7月前580
《论文阅读》Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset an
《论文阅读》Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark 前言 简介 创新
7月前600
【论文阅读】GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation（TPAMI 2023）
【论文链接】https:arxivabs2203.02177v2 【代码链接】GitHub - zeroQiaobaGCNet: GCNet, official pytorch implementation of our pap
7月前740
《论文阅读》BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation
《论文阅读》BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation 前言 简介 Suggestive Text Fine-grained Cl
7月前570
论文-《Making Personalized Recommendation through Conversation: Architecture Design and Recommendation》
题目Making Personalized Recommendation through Conversation:Architecture Design and Recommendation Methods简介论文旨在分享使用对话
7月前550
【三】情感对话 MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation 论文阅读
【三】情感支撑对话论文最近进展 Emotion Support Conversation 今天给大家介绍一下MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotiona
7月前640
论文阅读-自动程序修复-Keep the Conversation Going:Fixing 162 out of 337 bugs for $0.42 each using ChatGPT-2023
1 introduction文章标题翻译过来就是：只要两块五毛钱，ChatGPT帮你修bug。所以本文的核心思想就是，通过和chatgpt"对谈‘ÿ
7月前820
《论文阅读》EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa
《论文阅读》EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa 简介 思路出发点 任务定义 模型结构 构造输入 模型架构 训练过程 实验结果 结论
7月前580
关于conversation generation的论文笔记
对话模型此前的研究大致有三个方向：基于规则、基于信息检索、基于机器翻译。基于规则的对话系统，顾名思义，依赖于人们周密设计的规则，对话内容限制在特定领域下
7月前660
A Diversity-Promoting Objective Function for Neural Conversation Models论文阅读笔记
本文是李纪为的论文“A Diversity-Promoting Objective Function for Neural Conversation Models”阅读笔记。违章提出使用MMI代替原始的maximum likelihood作
7月前590
《论文阅读》SAPBERT: Speaker-Aware Pretrained BERT for Emotion Recognition in Conversation
《论文阅读》SAPBERT: Speaker-Aware Pretrained BERT for Emotion Recognition in Conversation 前言 简介 思路出发点 相关知识 Continuity 任务定义 预训
7月前510
CV-VIDEO经典论文解读|BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
论文标题： BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning BT-适配器：无需视频指令微调即可实现视频对话 论文链接： BT-A
7月前590
《论文阅读》DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
《论文阅读》DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition 简介 思路出发点 任务定义 模型结构 构造输入 模型架构 Utterance
7月前470
A Diversity-Promoting Objective Function for Neural Conversation Models 论文阅读零散笔记
A Diversity-Promoting Objective Function for Neural Conversation Models SEQ2SEQ模型用于conversational responses倾向于产生safe&am
7月前570
A Persona-Based Neural Conversation Model论文
问题：同样的问题，不同的表述，生成的回复就不一致。解决方法：在seq2seq的的decoder 加入了用户向量，类似词向量&
7月前510
论文笔记：Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
总所周知，许多对话系统的回复都比较单调或中性，降低了对话体验。而且，情感智能是人工智能至关重要的一部分，它能够感知，识别，理解用户的情感，并依此调节自身情感，给出符合情绪的表达。 该篇论文设计了一个情绪化的对话生成模型。该模型应用于开放领
7月前750
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey论文分享
今天分享的论文是《Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey》 原文链接：[2402.09283] Attacks,
7月前550
【论文】Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
《Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory》(Hao Zhou，Ts
7月前810