Li Gao
2024
Detecting Machine-Generated Text: Techniques and Challenges
Li Gao
|
Wenhan Xiong
|
Taewoo Kim
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts)
As AI-generated text increasingly resembles human-written content, the ability to detect machine-generated text becomes crucial in many applications. This tutorial aims to provide a comprehensive overview of text detection techniques, focusing on machine-generated text and deepfakes. We will discuss various methods for distinguishing between human-written and machine-generated text, including statistical methods, neural network-based techniques, and hybrid approaches. The tutorial will also cover the challenges in the detection process, such as dealing with evolving models and maintaining robustness against adversarial attacks. By the end of the session, attendees will have a solid understanding of current techniques and future directions in the field of text detection.
2022
Topology Imbalance and Relation Inauthenticity Aware Hierarchical Graph Attention Networks for Fake News Detection
Li Gao
|
Lingyun Song
|
Jie Liu
|
Bolin Chen
|
Xuequn Shang
Proceedings of the 29th International Conference on Computational Linguistics
Fake news detection is a challenging problem due to its tremendous real-world political and social impacts. Recent fake news detection works focus on learning news features from News Propagation Graph (NPG). However, little attention is paid to the issues of both authenticity of the relationships and topology imbalance in the structure of NPG, which trick existing methods and thus lead to incorrect prediction results. To tackle these issues, in this paper, we propose a novel Topology imbalance and Relation inauthenticity aware Hierarchical Graph Attention Networks (TR-HGAN) to identify fake news on social media. Specifically, we design a new topology imbalance smoothing strategy to measure the topology weight of each node. Besides, we adopt a hierarchical-level attention mechanism for graph convolutional learning, which can adaptively identify the authenticity of relationships by assigning appropriate weights to each of them. Experiments on real-world datasets demonstrate that TR-HGAN significantly outperforms state-of-the-art methods.
2019
Unsupervised Neural Machine Translation with Future Rewarding
Xiangpeng Wei
|
Yue Hu
|
Luxi Xing
|
Li Gao
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
In this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under the reinforcement learning framework, which aims to optimize the global word predictions for unsupervised neural machine translation. To this end, we design a novel reward function to characterize high-quality translations from two aspects: n-gram matching and semantic adequacy. The n-gram matching is defined as an alternative for the discrete BLEU metric, and the semantic adequacy is used to measure the adequacy of conveying the meaning of the source sentence to the target. During training, our model strives for earning higher rewards by learning to produce grammatically more accurate and semantically more adequate translations. Besides, a variational inference network (VIN) is proposed to constrain the corresponding sentences in two languages have the same or similar latent semantic code. On the widely used WMT’14 English-French, WMT’16 English-German and NIST Chinese-to-English benchmarks, our models respectively obtain 27.59/27.15, 19.65/23.42 and 22.40 BLEU points without using any labeled data, demonstrating consistent improvements over previous unsupervised NMT models.
Search
Co-authors
- Xiangpeng Wei 1
- Yue Hu 1
- Luxi Xing 1
- Lingyun Song 1
- Jie Liu 1
- show all...