no code implementations • ACL (IWSLT) 2021 • Xingshan Zeng, Liangyou Li, Qun Liu
We use a unified transformer architecture for our MultiST model, so that the data from different modalities (i. e., speech and text) and different tasks (i. e., Speech Recognition, Machine Translation, and Speech Translation) can be exploited to enhance the model’s ability.
no code implementations • NAACL (AutoSimTrans) 2022 • Xingshan Zeng, Pengfei Li, Liangyou Li, Qun Liu
This paper describes the system submitted to AutoSimTrans 2022 from Huawei Noah’s Ark Lab, which won the first place in the audio input track of the Chinese-English translation task.
no code implementations • Findings (ACL) 2022 • Tao Jin, Zhou Zhao, Meng Zhang, Xingshan Zeng
This paper attacks the challenging problem of sign language translation (SLT), which involves not only visual and textual understanding but also additional prior knowledge learning (i. e. performing style, syntax).
1 code implementation • 19 Feb 2024 • Yuxin Jiang, YuFei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang
Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention.
no code implementations • 8 Feb 2024 • Lingzhi Wang, Xingshan Zeng, Jinsong Guo, Kam-Fai Wong, Georg Gottlob
The aim of this study is to investigate Machine Unlearning (MU), a burgeoning field focused on addressing concerns related to neural models inadvertently retaining personal or sensitive data.
1 code implementation • 30 Jan 2024 • Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, YuFei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong
Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications.
1 code implementation • 30 Jan 2024 • Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu
The recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using tools.
1 code implementation • 31 Oct 2023 • Yuxin Jiang, YuFei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang
To fill this research gap, in this paper, we propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark for LLMs.
1 code implementation • 30 Oct 2023 • Wai-Chung Kwan, Xingshan Zeng, YuFei Wang, Yusen Sun, Liangyou Li, Lifeng Shang, Qun Liu, Kam-Fai Wong
In this paper, we propose M4LE, a Multi-ability, Multi-range, Multi-task, Multi-domain benchmark for Long-context Evaluation.
no code implementations • 9 Oct 2023 • Jianqiao Lu, Wenyong Huang, Nianzu Zheng, Xingshan Zeng, Yu Ting Yeung, Xiao Chen
For SLU, LaSyn improves our E2E baseline by absolute 4. 1% for intent classification accuracy and 3. 8% for slot filling SLU-F1 on SLURP, and absolute 4. 49% and 2. 25% for exact match (EM) and EM-Tree accuracies on STOP respectively.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 1 Oct 2023 • Jianqiao Lu, Wanjun Zhong, Wenyong Huang, YuFei Wang, Qi Zhu, Fei Mi, Baojun Wang, Weichao Wang, Xingshan Zeng, Lifeng Shang, Xin Jiang, Qun Liu
SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement.
1 code implementation • 24 Jul 2023 • YuFei Wang, Wanjun Zhong, Liangyou Li, Fei Mi, Xingshan Zeng, Wenyong Huang, Lifeng Shang, Xin Jiang, Qun Liu
(2) Training methodologies: a detailed review of the prevailing training methods employed for LLM alignment.
1 code implementation • 11 May 2023 • Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin
Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in the training set.
no code implementations • 27 Feb 2023 • Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng, Kam-Fai Wong
Conversational tutoring systems (CTSs) aim to help students master educational material with natural language interaction in the form of a dialog.
no code implementations • 17 Dec 2022 • Xingshan Zeng, Liangyou Li, Qun Liu
To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique.
1 code implementation • 11 Oct 2022 • Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, Kam-Fai Wong
Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.
no code implementations • 23 Sep 2022 • Lingzhi Wang, Shafiq Joty, Wei Gao, Xingshan Zeng, Kam-Fai Wong
In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model.
no code implementations • CVPR 2022 • Aoxiong Yin, Zhou Zhao, Weike Jin, Meng Zhang, Xingshan Zeng, Xiaofei He
In addition, we also explore zero-shot translation in sign language and find that our model can achieve comparable performance to the supervised BSLT model on some language pairs.
no code implementations • 8 Dec 2021 • Aoxiong Yin, Zhou Zhao, Jinglin Liu, Weike Jin, Meng Zhang, Xingshan Zeng, Xiaofei He
Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years.
1 code implementation • Findings (EMNLP) 2021 • Lingzhi Wang, Xingshan Zeng, Huang Hu, Kam-Fai Wong, Daxin Jiang
In recent years, world business in online discussions and opinion sharing on social media is booming.
1 code implementation • Findings (EMNLP) 2021 • Zhiming Mao, Xingshan Zeng, Kam-Fai Wong
In this work, we propose a news recommendation framework consisting of collaborative news encoding (CNE) and structural user encoding (SUE) to enhance news and user representation learning.
no code implementations • 31 Aug 2021 • Zhijie Lin, Zhou Zhao, Haoyuan Li, Jinglin Liu, Meng Zhang, Xingshan Zeng, Xiaofei He
Lip reading, aiming to recognize spoken sentences according to the given video of lip movements without relying on the audio stream, has attracted great interest due to its application in many scenarios.
no code implementations • 9 Aug 2021 • Minghan Wang, Yuxia Wang, Chang Su, Jiaxin Guo, Yingtao Zhang, Yujia Liu, Min Zhang, Shimin Tao, Xingshan Zeng, Liangyou Li, Hao Yang, Ying Qin
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
1 code implementation • EMNLP 2020 • Lingzhi Wang, Jing Li, Xingshan Zeng, Haisong Zhang, Kam-Fai Wong
Quotations are crucial for successful explanations and persuasions in interpersonal communications.
no code implementations • Findings (ACL) 2021 • Xingshan Zeng, Liangyou Li, Qun Liu
To bridge the modality gap between speech and text, RealTranS gradually downsamples the input speech with interleaved convolution and unidirectional Transformer layers for acoustic modeling, and then maps speech features into text space with a weighted-shrinking operation and a semantic encoder.
no code implementations • 1 Jun 2021 • Xingshan Zeng, Liangyou Li, Qun Liu
We use a unified transformer architecture for our MultiST model, so that the data from different modalities (i. e., speech and text) and different tasks (i. e., Speech Recognition, Machine Translation, and Speech Translation) can be exploited to enhance the model's ability.
1 code implementation • ACL 2021 • Lingzhi Wang, Xingshan Zeng, Kam-Fai Wong
To help individuals express themselves better, quotation recommendation is receiving growing attention.
no code implementations • ACL 2020 • Xingshan Zeng, Jing Li, Lu Wang, Zhiming Mao, Kam-Fai Wong
Trending topics in social media content evolve over time, and it is therefore crucial to understand social media users and their interpersonal communications in a dynamic manner.
no code implementations • IJCNLP 2019 • Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong
The prevalent use of social media leads to a vast amount of online conversations being produced on a daily basis.
1 code implementation • ACL 2019 • Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong
We hypothesize that both the context of the ongoing conversations and the users' previous chatting history will affect their continued interests in future engagement.
no code implementations • NAACL 2018 • Xingshan Zeng, Jing Li, Lu Wang, Nicholas Beauchamp, Sarah Shugars, Kam-Fai Wong
We propose a statistical model that jointly captures: (1) topics for representing user interests and conversation content, and (2) discourse modes for describing user replying behavior and conversation dynamics.