Cunli Mao

Dr. Cunli Mao

orcid

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 July 2023 in Neurocomputing
Verified
Journal Article
Open access
BLBin Li
Bin Li
ZSZhenqiu Shu
Zhenqiu Shu
YLYingbo Liu
Yingbo Liu
CMCunli Mao
Cunli Mao
SGShengxiang Gao
Shengxiang Gao
ZYZhengtao Yu
Zhengtao Yu

1 January 2024
Verified
Conference Paper
Open access
PDF file
CCChuanqi Cheng
Chuanqi Cheng
QTQuan Tu
Quan Tu
WWWei Wu
Wei Wu
SSShuo Shang
Shuo Shang
CMCunli Mao
Cunli Mao
RYRui Yan
Rui Yan
Chuanqi Cheng, Quan Tu, Wei Wu, Shuo Shang, Cunli Mao, Zhengtao Yu, Rui Yan. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

28 June 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
LWLinqin Wang
Linqin Wang
XHXiang Huang
Xiang Huang
ZYZhengtao Yu
Zhengtao Yu
HPHao Peng
Hao Peng
SGShengxiang Gao
Shengxiang Gao
PYPhilip S. Yu
Philip S. Yu
Text normalization (TN) is a crucial preprocessing step in text-to-speech synthesis, which pertains to the accurate pronunciation of numbers and symbols within the text. Existing neural network-based TN methods have shown significant success in rich-resource languages. However, these methods are data-driven and highly rely on a large number of labeled datasets, which are not practical in zero-resource settings. Rule-based weighted finite-state transducers (WFST) are a common measure for zero-shot TN, but WFST-based TN approaches encounter challenges with ambiguous input, particularly in cases where the normalized form is context-dependent. On the other hand, conventional neural TN methods suffer from unrecoverable errors. In this paper, we propose ZSTN, a novel zero-shot TN framework based on cross-lingual knowledge distillation, which utilizes annotated data to train the teacher model on rich-resource language and unlabelled data to train the student model on zero-resource language. Furthermore, it incorporates expert knowledge from WFST into a knowledge distillation neural network. Concretely, a TN model with WFST pseudo-labels augmentation is trained as a teacher model in the source language. Subsequently, the student model is supervised by soft-labels from the teacher model and WFST pseudo-labels from the target language. By leveraging cross-lingual knowledge distillation, we address contextual ambiguity in the text, while WFST mitigates unrecoverable errors of the neural model. Additionally, ZSTN is adaptable to different zero-resource languages by using the joint loss function for the teacher model and WFST constraints. We also release a zero-shot text normalization dataset in five languages. We compare ZSTN with seven zero-shot TN benchmarks on public datasets in four languages for the teacher model and zero-shot datasets in five languages for the student model. The results demonstrate that the proposed ZSTN excels in performance without the need for labeled data. All datasets and codes used for this work are released at https://github.com/wlq2019/Zero-Shot-Text-Normalization .

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YLYuxuan Liu
Yuxuan Liu
HSHongda Sun
Hongda Sun
WGWenya Guo
Wenya Guo
XXXinyan Xiao
Xinyan Xiao
CMCunli Mao
Cunli Mao
RYRui Yan
Rui Yan
Complex claim fact-checking performs a crucial role in disinformation detection. However, existing fact-checking methods struggle with claim vagueness, specifically in effectively handling latent information and complex relations within claims. Moreover, evidence redundancy, where non-essential information complicates the verification process, remains a significant issue. To tackle these limitations, we propose Bilateral Defusing Verification (BiDeV), a novel fact-checking working-flow framework integrating multiple role-played LLMs to mimic the human-expert fact-checking process. BiDeV consists of two main modules: Vagueness Defusing identifies latent information and resolves complex relations to simplify the claim, and Redundancy Defusing eliminates redundant content to enhance the evidence quality. Extensive experimental results on two widely used challenging fact-checking benchmarks (Hover and Feverous-s) demonstrate that our BiDeV can achieve the best performance under both gold and open settings. This highlights the effectiveness of BiDeV in handling complex claims and ensuring precise fact-checking.

1 June 2024 in International Journal of Machine Learning and Cybernetics
Verified
Journal Article
Closed access
PDF file
ZWZhenhan Wang
Zhenhan Wang
RSRan Song
Ran Song
ZYZhengtao Yu
Zhengtao Yu
CMCunli Mao
Cunli Mao
SGShengxiang Gao
Shengxiang Gao

19 October 2021 in Neural Processing Letters
Verified
Journal Article
Closed access
PDF file
LLLingling Li
Lingling Li
CZChangwen Zheng
Changwen Zheng
CMCunli Mao
Cunli Mao
HDHaibo Deng
Haibo Deng
TJTaisong Jin
Taisong Jin