no code implementations • 23 May 2024 • Jinhui Ye, Xing Wang, Wenxiang Jiao, Junwei Liang, Hui Xiong
In this paper, we identify a representation density problem that could be a bottleneck in restricting the performance of gloss-free SLT.
Contrastive Learning Gloss-free Sign Language Translation +2
1 code implementation • 18 Mar 2024 • Jen-tse Huang, Eric John Li, Man Ho Lam, Tian Liang, Wenxuan Wang, Youliang Yuan, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Michael R. Lyu
Decision-making, a complicated task requiring various types of abilities, presents an excellent framework for assessing Large Language Models (LLMs).
no code implementations • 12 Feb 2024 • Zhengsheng Guo, Zhiwei He, Wenxiang Jiao, Xing Wang, Rui Wang, Kehai Chen, Zhaopeng Tu, Yong Xu, Min Zhang
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.
1 code implementation • 23 Jan 2024 • Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, Zhaopeng Tu
In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training.
no code implementations • 1 Jan 2024 • Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael R. Lyu
In addition, the test cases of LogicAsker can be further used to design demonstration examples for in-context learning, which effectively improves the logical reasoning ability of LLMs, e. g., 10\% for GPT-4.
no code implementations • 1 Jan 2024 • Wenxuan Wang, Juluan Shi, Zhaopeng Tu, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael R. Lyu
Current methods for evaluating LLMs' veracity are limited by test data leakage or the need for extensive human labor, hindering efficient and accurate error detection.
1 code implementation • 31 Oct 2023 • Tian Liang, Zhiwei He, Jen-tse Huang, Wenxuan Wang, Wenxiang Jiao, Rui Wang, Yujiu Yang, Zhaopeng Tu, Shuming Shi, Xing Wang
Ideally, an advanced agent should possess the ability to accurately describe a given word using an aggressive description while concurrently maximizing confusion in the conservative description, enhancing its participation in the game.
no code implementations • 19 Oct 2023 • Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu, Michael R. Lyu
This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e. g., ChatGPT).
1 code implementation • 2 Oct 2023 • Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael R. Lyu
In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice.
1 code implementation • 2 Oct 2023 • Jen-tse Huang, Wenxuan Wang, Eric John Li, Man Ho Lam, Shujie Ren, Youliang Yuan, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu
Large Language Models (LLMs) have recently showcased their remarkable capacities, not only in natural language processing tasks but also across diverse domains such as clinical medicine, legal consultation, and education.
1 code implementation • 12 Aug 2023 • Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Pinjia He, Shuming Shi, Zhaopeng Tu
We propose a novel framework CipherChat to systematically examine the generalizability of safety alignment to non-natural languages -- ciphers.
1 code implementation • 7 Aug 2023 • Jen-tse Huang, Man Ho Lam, Eric John Li, Shujie Ren, Wenxuan Wang, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu
Evaluating Large Language Models' (LLMs) anthropomorphic capabilities has become increasingly important in contemporary discourse.
1 code implementation • 31 May 2023 • Jen-tse Huang, Wenxuan Wang, Man Ho Lam, Eric John Li, Wenxiang Jiao, Michael R. Lyu
Recent research has extended beyond assessing the performance of Large Language Models (LLMs) to examining their characteristics from a psychological standpoint, acknowledging the necessity of understanding their behavioral characteristics.
1 code implementation • 30 May 2023 • Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, Shuming Shi
To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
1 code implementation • 18 May 2023 • Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Hui Xiong
It has been a challenging task due to the modality gap between sign videos and texts and the data scarcity of labeled data.
Ranked #4 on Sign Language Translation on CSL-Daily
2 code implementations • 6 May 2023 • Zhiwei He, Tian Liang, Wenxiang Jiao, Zhuosheng Zhang, Yujiu Yang, Rui Wang, Zhaopeng Tu, Shuming Shi, Xing Wang
Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation.
1 code implementation • 5 Apr 2023 • Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu
Therefore, we propose ParroT, a framework to enhance and regulate the translation abilities during chat based on open-source LLMs (e. g., LLaMA), human-written translation and feedback data.
no code implementations • 15 Mar 2023 • Haoran Wu, Wenxuan Wang, Yuxuan Wan, Wenxiang Jiao, Michael Lyu
ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions.
1 code implementation • 20 Jan 2023 • Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Xing Wang, Shuming Shi, Zhaopeng Tu
By evaluating on a number of benchmark test sets, we find that ChatGPT performs competitively with commercial translation products (e. g., Google Translate) on high-resource European languages but lags behind significantly on low-resource or distant languages.
1 code implementation • 24 Oct 2022 • Yifan Hou, Wenxiang Jiao, Meizhen Liu, Carl Allen, Zhaopeng Tu, Mrinmaya Sachan
Specifically, we introduce a lightweight adapter set to enhance MLLMs with cross-lingual entity alignment and facts from MLKGs for many languages.
1 code implementation • 18 Oct 2022 • Wenxiang Jiao, Zhaopeng Tu, Jiarui Li, Wenxuan Wang, Jen-tse Huang, Shuming Shi
This paper describes Tencent's multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages.
1 code implementation • 13 Oct 2022 • Jinhui Ye, Wenxiang Jiao, Xing Wang, Zhaopeng Tu
In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data.
no code implementations • 20 May 2022 • Wenxuan Wang, Wenxiang Jiao, Shuo Wang, Zhaopeng Tu, Michael R. Lyu
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation (MNMT) system.
no code implementations • ACL 2022 • Wenxuan Wang, Wenxiang Jiao, Yongchang Hao, Xing Wang, Shuming Shi, Zhaopeng Tu, Michael Lyu
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT).
1 code implementation • ACL 2021 • Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Shuming Shi, Michael R. Lyu, Irwin King
In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.
1 code implementation • NAACL 2021 • Yongchang Hao, Shilin He, Wenxiang Jiao, Zhaopeng Tu, Michael Lyu, Xing Wang
In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
1 code implementation • EMNLP 2020 • Wenxiang Jiao, Xing Wang, Shilin He, Irwin King, Michael R. Lyu, Zhaopeng Tu
First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Wenxiang Jiao, Michael R. Lyu, Irwin King
Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task.
Emotion Recognition in Conversation General Classification +2
1 code implementation • 20 Nov 2019 • Wenxiang Jiao, Michael R. Lyu, Irwin King
We propose an Attention Gated Hierarchical Memory Network (AGHMN) to address the problems of prior work: (1) Commonly used convolutional neural networks (CNNs) for utterance feature extraction are less compatible in the memory modules; (2) Unidirectional gated recurrent units (GRUs) only allow each historical utterance to have context before it, preventing information propagation in the opposite direction; (3) The Soft Attention for summarizing loses the positional and ordering information of memories, regardless of how the memory bank is built.
Ranked #44 on Emotion Recognition in Conversation on IEMOCAP
no code implementations • 21 Oct 2019 • Wenxiang Jiao, Irwin King, Michael R. Lyu
Word2Vec is the most popular model for word representation and has been widely investigated in literature.
1 code implementation • 20 Oct 2019 • Wenxiang Jiao, Michael R. Lyu, Irwin King
Witnessing the success of transfer learning in natural language process (NLP), we propose to pre-train a context-dependent encoder (CoDE) for ULER by learning from unlabeled conversation data.
1 code implementation • NAACL 2019 • Wenxiang Jiao, Haiqin Yang, Irwin King, Michael R. Lyu
In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured.