Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Zhang, Wei Nan"'
Publikováno v:
ACM Trans. Inf. Syst. 41, 1, Article 15 (January 2023)
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation
Externí odkaz:
http://arxiv.org/abs/2410.20766
The attention mechanism plays an important role in the machine reading comprehension (MRC) model. Here, we describe a pipeline for building an MRC model with a pretrained language model and visualizing the effect of each attention zone in different l
Externí odkaz:
http://arxiv.org/abs/2410.20652
Publikováno v:
ACM Trans. Inf. Syst. 41, 3, Article 68 (July 2023)
With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims to generate
Externí odkaz:
http://arxiv.org/abs/2410.20174
Publikováno v:
ACM Transactions on Information Systems, Volume 42, Issue 2, 08 November 2023
Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper, we propos
Externí odkaz:
http://arxiv.org/abs/2410.15970
Autor:
Liu, Yuanxing, Zhang, Wei-Nan, Chen, Yifan, Zhang, Yuchi, Bai, Haopeng, Feng, Fan, Cui, Hengbin, Li, Yongbin, Che, Wanxiang
E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accura
Externí odkaz:
http://arxiv.org/abs/2310.14626
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI. Previous approaches are mainly based on fine small-scale language models. With the advent of ChatGPT, the app
Externí odkaz:
http://arxiv.org/abs/2310.05140
CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLI
Externí odkaz:
http://arxiv.org/abs/2203.07190
Publikováno v:
iScience 25(5), 2022
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs). However, the internal mechanism of these artifacts remains unclear, p
Externí odkaz:
http://arxiv.org/abs/2108.11574
Publikováno v:
In Cell Reports Physical Science 17 April 2024 5(4)
Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue m
Externí odkaz:
http://arxiv.org/abs/2106.06169