中文
相关论文

相关论文: Inconsistent dialogue responses and how to recover…

200 篇论文

Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue…

计算与语言 · 计算机科学 2022-03-08 Leyang Cui , Fandong Meng , Yijin Liu , Jie Zhou , Yue Zhang

Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…

数据库 · 计算机科学 2023-12-27 Jasmin Mousavi , Arash Termehchy

Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We…

计算与语言 · 计算机科学 2019-01-21 Sean Welleck , Jason Weston , Arthur Szlam , Kyunghyun Cho

ChatGPT has gained a huge popularity since its introduction. Its positive aspects have been reported through many media platforms, and some analyses even showed that ChatGPT achieved a decent grade in professional exams, adding extra…

计算与语言 · 计算机科学 2023-11-15 Myeongjun Erik Jang , Thomas Lukasiewicz

Maintaining a consistent attribute profile is crucial for dialogue agents to naturally converse with humans. Existing studies on improving attribute consistency mainly explored how to incorporate attribute information in the responses, but…

计算与语言 · 计算机科学 2021-05-18 Haoyu Song , Yan Wang , Wei-Nan Zhang , Zhengyu Zhao , Ting Liu , Xiaojiang Liu

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

Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation…

计算与语言 · 计算机科学 2021-06-21 Lingzhi Wang , Jing Li , Xingshan Zeng , Haisong Zhang , Kam-Fai Wong

Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT. Despite significant advancements, the limited scale and diversity of current persona dialogue datasets…

计算与语言 · 计算机科学 2025-02-20 Mengze Hong , Chen Jason Zhang , Chaotao Chen , Rongzhong Lian , Di Jiang

Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures.…

计算与语言 · 计算机科学 2023-02-28 Ruijun Chen , Jin Wang , Liang-Chih Yu , Xuejie Zhang

The study illustrates a first step towards an ongoing work aimed at developing a dataset of dialogues potentially useful for customer service conversation management between humans and AI chatbots. The approach exploits ChatGPT 3.5 to…

人机交互 · 计算机科学 2025-01-03 Alfredo Cuzzocrea , Giovanni Pilato , Pablo Garcia Bringas

One challenge for evaluating current sequence- or dialogue-level chatbots, such as Empathetic Open-domain Conversation Models, is to determine whether the chatbot performs in an emotionally consistent way. The most recent work only…

计算与语言 · 计算机科学 2021-12-06 Chenxiao Liu , Guanzhi Deng , Tao Ji , Difei Tang , Silai Zheng

Goal-oriented proactive dialogue systems are designed to guide user conversations seamlessly towards specific objectives by planning a goal-oriented path. However, previous research has focused predominantly on optimizing these paths while…

计算与语言 · 计算机科学 2025-06-19 Didi Zhang , Yaxin Fan , Peifeng Li , Qiaoming Zhu

Conversation systems accommodate diverse users with unique personalities and distinct writing styles. Within the domain of multi-turn dialogue modeling, this work studies the impact of varied utterance lengths on the quality of subsequent…

计算与语言 · 计算机科学 2024-02-02 Yufei Tao , Tiernan Mines , Ameeta Agrawal

Though chatbots based on large neural models can often produce fluent responses in open domain conversations, one salient error type is contradiction or inconsistency with the preceding conversation turns. Previous work has treated…

计算与语言 · 计算机科学 2022-07-26 Di Jin , Sijia Liu , Yang Liu , Dilek Hakkani-Tur

Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to…

计算与语言 · 计算机科学 2021-11-02 James D. Finch , Sarah E. Finch , Jinho D. Choi

Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation.…

计算与语言 · 计算机科学 2018-06-19 Svitlana Vakulenko , Maarten de Rijke , Michael Cochez , Vadim Savenkov , Axel Polleres

Task-oriented dialogues must maintain consistency both within the dialogue itself, ensuring logical coherence across turns, and with the conversational domain, accurately reflecting external knowledge. We propose to conceptualize dialogue…

计算与语言 · 计算机科学 2024-07-17 Tiziano Labruna , Bernardo Magnini

Large language models, like ChatGPT, have shown remarkable capability in many downstream tasks, yet their ability to understand discourse structures of dialogues remains less explored, where it requires higher level capabilities of…

计算与语言 · 计算机科学 2024-03-06 Yaxin Fan , Feng Jiang , Peifeng Li , Haizhou Li

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…

计算与语言 · 计算机科学 2018-09-24 Nikita Moghe , Siddhartha Arora , Suman Banerjee , Mitesh M. Khapra

Despite tremendous advancements in dialogue systems, stable evaluation still requires human judgments producing notoriously high-variance metrics due to their inherent subjectivity. Moreover, methods and labels in dialogue evaluation are…

计算与语言 · 计算机科学 2023-08-01 Sarah E. Finch , James D. Finch , Jinho D. Choi
‹ 上一页 1 2 3 10 下一页 ›