Tiezheng Yu

Tiezheng Yu

Auto-generated profile, based on publicly available information

Tiezheng Yu

Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
3 March 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
ZJZiwei Ji
Ziwei Ji
NLNayeon Lee
Nayeon Lee
RFRita Frieske
Rita Frieske
TYTiezheng Yu
Tiezheng Yu
DSDan Su
Dan Su
PFPascale Fung
Pascale Fung
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before.In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

1 January 2021
Verified
Conference Paper
Open access
PDF file
DSDan Su
Dan Su
TYTiezheng Yu
Tiezheng Yu
PFPascale Fung
Pascale Fung
Dan Su, Tiezheng Yu, Pascale Fung. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.

1 January 2023
Verified
Conference Paper
Open access
PDF file
TYTiezheng Yu
Tiezheng Yu
ZJZiwei Ji
Ziwei Ji
PFPascale Fung
Pascale Fung
Tiezheng Yu, Ziwei Ji, Pascale Fung. Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings). 2023.

19 July 2026
Verified
Conference Paper
Open access
HCHongru Cai
Hongru Cai
YLYongqi Li
Yongqi Li
TYTiezheng Yu
Tiezheng Yu
FZFengbin Zhu
Fengbin Zhu
WWWenjie Wang
Wenjie Wang
WLWenjie Li
Wenjie Li

14 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
YBYejin Bang
Yejin Bang
TYTiezheng Yu
Tiezheng Yu
AMAndrea Madotto
Andrea Madotto
ZLZhaojiang Lin
Zhaojiang Lin
MDMona Diab
Mona Diab
PFPascale Fung
Pascale Fung
Many NLP classification tasks, such as sexism/racism detection or toxicity detection, are based on human values. Yet, human values can vary under diverse cultural conditions. Therefore, we introduce a framework for value-aligned classification that performs prediction based on explicitly written human values in the command. Along with the task, we propose a practical approach that distills value-aligned knowledge from large-scale language models (LLMs) to construct value-aligned classifiers in two steps. First, we generate value-aligned training data from LLMs by prompt-based few-shot learning. Next, we fine-tune smaller classification models with the generated data for the task. Empirical results show that our VA-Models surpass multiple baselines by at least 15.56% on the F1-score, including few-shot learning with OPT-175B and existing text augmentation methods. We suggest that using classifiers with explicit human value input improves both inclusivity & explainability in AI.

6 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
WDWenliang Dai
Wenliang Dai
SCSamuel Cahyawijaya
Samuel Cahyawijaya
TYTiezheng Yu
Tiezheng Yu
EBElham J Barezi
Elham J Barezi
PFPascale Fung
Pascale Fung
With the rise of deep learning and intelligent vehicles, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities. In-car smart assistants should be able to process general as well as car-related commands and perform corresponding actions, which eases driving and improves safety. However, in this research field, most datasets are in major languages, such as English and Chinese. There is a huge data scarcity issue for low-resource languages, hindering the development of research and applications for broader communities. Therefore, it is crucial to have more benchmarks to raise awareness and motivate the research in low-resource languages. To mitigate this problem, we collect a new dataset, namely Cantonese In-car Audio-Visual Speech Recognition (CI-AVSR), for in-car speech recognition in the Cantonese language with video and audio data. Together with it, we propose Cantonese Audio-Visual Speech Recognition for In-car Commands as a new challenge for the community to tackle low-resource speech recognition under in-car scenarios.