中文
相关论文

相关论文: Enhancing Target-Guided Proactive Dialogue Systems…

200 篇论文

Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years. The duration of gaps between conversations dictates which topics are relevant and which…

计算与语言 · 计算机科学 2023-10-25 Qiang Zhang , Jason Naradowsky , Yusuke Miyao

Personalizing dialogue agents is important for dialogue systems to generate more specific, consistent, and engaging responses. However, most current dialogue personalization approaches rely on explicit persona descriptions during inference,…

计算与语言 · 计算机科学 2021-12-01 Wangchunshu Zhou , Qifei Li , Chenle Li

Enterprise conversational AI systems are becoming increasingly popular to assist users in completing daily tasks such as those in marketing and customer management. However, new users often struggle to ask effective questions, especially in…

计算与语言 · 计算机科学 2024-12-17 Xiaobin Shen , Daniel Lee , Sumit Ranjan , Sai Sree Harsha , Pawan Sevak , Yunyao Li

The rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting users' analytical and interaction intents. While language…

人机交互 · 计算机科学 2025-04-17 Juntong Chen , Jiang Wu , Jiajing Guo , Vikram Mohanty , Xueming Li , Jorge Piazentin Ono , Wenbin He , Liu Ren , Dongyu Liu

We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with…

计算与语言 · 计算机科学 2020-10-20 Xueliang Zhao , Wei Wu , Can Xu , Chongyang Tao , Dongyan Zhao , Rui Yan

Dialog modelling faces a difficult trade-off. Models are trained on a large amount of text, yet their responses need to be limited to a desired scope and style of a dialog agent. Because the datasets used to achieve the former contain…

计算与语言 · 计算机科学 2022-09-23 Josef Valvoda , Yimai Fang , David Vandyke

Recently, the topic-grounded dialogue (TGD) system has become increasingly popular as its powerful capability to actively guide users to accomplish specific tasks through topic-guided conversations. Most existing works utilize side…

计算与语言 · 计算机科学 2024-06-05 Shixuan Fan , Wei Wei , Xiaofei Wen , Xianling Mao , Jixiong Chen , Dangyang Chen

Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking…

计算与语言 · 计算机科学 2024-11-19 Jing Yang Lee , Seokhwan Kim , Kartik Mehta , Jiun-Yu Kao , Yu-Hsiang Lin , Arpit Gupta

Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures…

计算与语言 · 计算机科学 2021-09-17 Chia-Hsuan Lee , Hao Cheng , Mari Ostendorf

Cyber-physical systems like autonomous vehicles are tested in simulation before deployment, using domain-specific programs for scenario specification. To aid the testing of autonomous vehicles in simulation, we design a natural language…

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface…

计算与语言 · 计算机科学 2024-02-20 Tom Bocklisch , Thomas Werkmeister , Daksh Varshneya , Alan Nichol

Conversational grounding is a collaborative mechanism for establishing mutual knowledge among participants engaged in a dialogue. This experimental study analyzes information-seeking conversations to investigate the capabilities of large…

计算与语言 · 计算机科学 2024-06-05 Kristiina Jokinen , Phillip Schneider , Taiga Mori

Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…

计算与语言 · 计算机科学 2018-08-08 Suyoun Kim , Florian Metze

The manual modeling of complex systems is a daunting task; and although a plethora of methods exist that mitigate this issue, the problem remains very difficult. Recent advances in generative AI have allowed the creation of general-purpose…

软件工程 · 计算机科学 2024-01-05 David Harel , Guy Katz , Assaf Marron , Smadar Szekely

Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be…

计算与语言 · 计算机科学 2020-08-14 Qingkai Min , Libo Qin , Zhiyang Teng , Xiao Liu , Yue Zhang

Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the…

计算与语言 · 计算机科学 2022-12-26 Zhitong Yang , Xing Ma , Anqi Liu , Zheyu Zhang

Intent modelling has become an important part of modern dialogue systems. With the rapid expansion of practical dialogue systems and virtual assistants, such as Amazon Alexa, Apple Siri, and Google Assistant, the interest has only…

计算与语言 · 计算机科学 2021-05-11 Sindre André Jacobsen , Anton Ragni

Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios. However, existing research primarily focuses on either…

计算与语言 · 计算机科学 2023-01-26 Kushal Chawla , Weiyan Shi , Jingwen Zhang , Gale Lucas , Zhou Yu , Jonathan Gratch

Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems. An example is the frame tracking task, which requires recording multiple frames, one for each user goal set during the dialogue. This allows a…

计算与语言 · 计算机科学 2017-06-07 Hannes Schulz , Jeremie Zumer , Layla El Asri , Shikhar Sharma

This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that…

人机交互 · 计算机科学 2023-07-06 Andreas Göldi , Roman Rietsche