Xiaochun Zhang

Xiaochun Zhang

Auto-generated profile, based on publicly available information

Xiaochun Zhang

School of Management Science and Computer, Anhui University of Finance and Economics, Bengbu, Anhui, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2022 in IEEE Access
Verified
Journal Article
Open access
CLChen Li
Chen Li
XZXiaochun Zhang
Xiaochun Zhang
Dimitrios ChrysostomouDimitrios Chrysostomou
Dimitrios Chrysostomou
Hongji YangHongji Yang
Hongji Yang
Despite the fact that task-oriented conversation systems have received much attention from the dialogue research community, only a handful of them have been studied in a real-world manufacturing context using industrial robots. One stumbling block is the lack of a domain-specific discourse corpus for training these systems. Another difficulty is that earlier attempts to integrate natural language interfaces (such as chatbots) into the industrial sector have primarily focused on task completion rates. When designing a dialogue system for social robots, the user experience is prioritized above industrial robots. We provide the Industrial Robots Domain Wizard-of-Oz dataset (IRWoZ) to overcome these challenges, a fully-labeled discourse dataset covering four robotics domains. It delivers simulated discussions between shop floor workers and industrial robots, with over 401 dialogues, to promote language-assisted Human-Robot Interaction (HRI) in industrial settings. Small talk concepts and human-to-human conversation strategies are provided to support humanlike answer generation and give a more natural and adaptable dialogue environment to increase user experience and engagement. Finally, we propose and evaluate an end-to-end Task-oriented Dialogue for Industrial Robots (ToD4IR) using two types of pre-trained backbone models: GPT-2 and GPT-Neo, on the IRWoZ dataset. ToD4IR’s performance in a real manufacturing context was validated through a series of trials. Our experiments demonstrate that ToD4IR outperforms three downstream task-oriented dialogue tasks, i.e., dialogue state tracking, dialogue act generation, and response generation, on the IRWoZ dataset. Our source code of ToD4IR and the IRWoZ dataset is accessible at https://github.com/lcroy/ToD4IR for reproducible research.

4 February 2013 in Meta : Journal Des Traducteursmeta : / Translators’ Journal
Verified
Journal Article
Open access
PDF file
XZXiaochun Zhang
Xiaochun Zhang
Censorship and translation is a topic that has received substantial attention in academic circles in recent years. Although much of the research has focused on the interrelationship between these two areas, censorship systems and their influence on audiovisual translation, especially digital games localisation, has not been fully examined within the scope of translation studies. This article aims to fill that gap by investigating censorial operations on digital games against the socio-cultural background of Mainland China. It will provide an overview of the Chinese censorship system, with a particular focus on the censoring authorities, their reviewing procedures and methods, including the regulations and standards on game content. It questions the extent to which censorship influences games localisation in practice and concludes that game localisers tend to perform stringent self-censorship when the censorship system itself lacks transparency.

20 March 2023 in IEEE Access
Verified
Journal Article
Open access
CLChen Li
Chen Li
Dimitrios ChrysostomouDimitrios Chrysostomou
Dimitrios Chrysostomou
XZXiaochun Zhang
Xiaochun Zhang
Hongji YangHongji Yang
Hongji Yang
Enabling a flexible and natural human-robot interaction (HRI) for industrial robots is a critical yet challenging task that can be facilitated by the use of conversational artificial intelligence (AI). Prior research has concentrated on strengthening interactions through the deployment of social robots, while disregarding the capabilities required to boost the flexibility and user experience associated with human-robot collaboration (HRC) on manufacturing tasks. One of the main challenges is the lack of publicly available industrial-oriented dialogue datasets for the training of conversational AI. In this work, we present an industrial robot wizard-of-Oz dialoguing dataste (IRWoZ) focused on enabling HRC in manufacturing tasks. The dataset covers four domains: assembly, transportation, position, and relocation. It is created using the Wizard-of-Oz technique to be less noisy. We manually constructed, annotated and validated dialogue segments (e.g., intentions, slots, annotations), as well as the responses. Building upon the proposed dataset, we benchmark it on the state-of-the-art (SoTA) language models, generative pre-trained (GPT-2) models, on dialogue state tracking and response generation tasks. We expect that the IRWoZ dataset will facilitate exciting ongoing dialogue research and we provide it freely accessible at https://github.com/lcroy/ToD4IR/tree/main/dataset.

22 August 2019
Verified
Book Chapter
Closed access
PDF file
LZLichen Zhang
Lichen Zhang
XZXiaochun Zhang
Xiaochun Zhang
SYSui Yu
Sui Yu
LGLongjiang Guo
Longjiang Guo
PLPeng Li
Peng Li
XWXiaoming Wang
Xiaoming Wang

21 July 2017
Verified
Conference Paper
Closed access
PDF file
XZXiaochun Zhang
Xiaochun Zhang
CLChuancai Liu
Chuancai Liu

31 December 2017 in The Journal of Internationalization and Localization
Verified
Journal Article
Open access
XZXiaochun Zhang
Xiaochun Zhang
SSSamuel Strong
Samuel Strong