no code implementations • EACL (WASSA) 2021 • Wazir Ali, Naveed Ali, Yong Dai, Jay Kumar, Saifullah Tumrani, Zenglin Xu
In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers.
no code implementations • Findings (ACL) 2022 • Yong Dai, Linyang Li, Cong Zhou, Zhangyin Feng, Enbo Zhao, Xipeng Qiu, Piji Li, Duyu Tang
The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters.
1 code implementation • 16 Apr 2024 • Pengyu Cheng, Tianhao Hu, Han Xu, Zhisong Zhang, Yong Dai, Lei Han, Nan Du
Hence, we are curious about whether LLMs' reasoning ability can be further enhanced by Self-Play in this Adversarial language Game (SPAG).
no code implementations • 14 Apr 2024 • Quanxiu Wang, Hui Huang, Mingjie Wang, Yong Dai, Jinzuomu Zhong, Benlai Tang
Furthermore, a parallelized TTS frontend model is delicately devised to execute TN, PD, and PBP prediction tasks, respectively in the second stage.
no code implementations • 26 Feb 2024 • Anchun Gui, Jian Li, Yong Dai, Nan Du, Han Xiao
Meanwhile, we propose a novel tool sampling strategy to enhance the generalizability of LLMs over unseen tools.
no code implementations • 8 Feb 2024 • Mingjie Wang, Jun Zhou, Yong Dai, Eric Buys, Minglun Gong
Recently, Class-Agnostic Counting (CAC) problem has garnered increasing attention owing to its intriguing generality and superior efficiency compared to Category-Specific Counting (CSC).
1 code implementation • 30 Jan 2024 • Bang Yang, Yong Dai, Xuxin Cheng, Yaowei Li, Asif Raza, Yuexian Zou
To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training.
1 code implementation • 25 Jan 2024 • Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.
no code implementations • 22 Dec 2023 • Zhangyin Feng, Runyi Hu, Liangxin Liu, Fan Zhang, Duyu Tang, Yong Dai, Xiaocheng Feng, Jiwei Li, Bing Qin, Shuming Shi
Compared with autoregressive baselines that needs to run one thousand times, our model only runs 16 times to generate images of competitive quality with an order of magnitude lower inference latency.
1 code implementation • 12 Dec 2023 • Dun Zeng, Yong Dai, Pengyu Cheng, Longyue Wang, Tianhao Hu, Wanshun Chen, Nan Du, Zenglin Xu
Our analysis reveals a correlation between the calibration performance of reward models (RMs) and the alignment performance of LLMs.
1 code implementation • 14 Nov 2023 • Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Tianhao Hu, Peixin Cao, Nan Du
Human preference alignment is essential to improve the interaction quality of large language models (LLMs).
1 code implementation • 9 Nov 2023 • Shuyi Xie, Wenlin Yao, Yong Dai, Shaobo Wang, Donlin Zhou, Lifeng Jin, Xinhua Feng, Pengzhi Wei, Yujie Lin, Zhichao Hu, Dong Yu, Zhengyou Zhang, Jing Nie, Yuhong Liu
We construct a hierarchical task tree encompassing 7 major areas covering over 200 categories and over 800 tasks, which covers diverse capabilities such as question answering, reasoning, multiturn dialogue, and text generation, to evaluate LLMs in a comprehensive and in-depth manner.
1 code implementation • 6 Sep 2023 • Pengyu Cheng, Jiawen Xie, Ke Bai, Yong Dai, Nan Du
Besides, from the perspective of data efficiency, we propose a three-stage customized RM learning scheme, then empirically verify its effectiveness on both general preference datasets and our DSP set.
no code implementations • 25 Aug 2023 • Jiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai, Nan Du
Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the input sequence length.
no code implementations • 28 Jun 2023 • Zhangyin Feng, Yong Dai, Fan Zhang, Duyu Tang, Xiaocheng Feng, Shuangzhi Wu, Bing Qin, Yunbo Cao, Shuming Shi
Traditional multitask learning methods basically can only exploit common knowledge in task- or language-wise, which lose either cross-language or cross-task knowledge.
1 code implementation • 20 Dec 2022 • Zhuo Zhang, Yuanhang Yang, Yong Dai, Lizhen Qu, Zenglin Xu
To facilitate the research of PETuning in FL, we also develop a federated tuning framework FedPETuning, which allows practitioners to exploit different PETuning methods under the FL training paradigm conveniently.
no code implementations • 20 Aug 2022 • Yanjie Gou, Yinjie Lei, Lingqiao Liu, Yong Dai, Chunxu Shen, Yongqi Tong
Existing works usually formulate the span detection as a 1D token tagging problem, and model the sentiment recognition with a 2D tagging matrix of token pairs.
no code implementations • 3 Aug 2022 • Shuming Shi, Enbo Zhao, Duyu Tang, Yan Wang, Piji Li, Wei Bi, Haiyun Jiang, Guoping Huang, Leyang Cui, Xinting Huang, Cong Zhou, Yong Dai, Dongyang Ma
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
no code implementations • 12 May 2022 • Yong Dai, Duyu Tang, Liangxin Liu, Minghuan Tan, Cong Zhou, Jingquan Wang, Zhangyin Feng, Fan Zhang, Xueyu Hu, Shuming Shi
Moreover, our model supports self-supervised pretraining with the same sparsely activated way, resulting in better initialized parameters for different modalities.
no code implementations • 26 Apr 2022 • Cong Zhou, Yong Dai, Duyu Tang, Enbo Zhao, Zhangyin Feng, Li Kuang, Shuming Shi
We achieve this by introducing a special token \texttt{[null]}, the prediction of which stands for the non-existence of a word.
1 code implementation • 12 Mar 2022 • Linyang Li, Yong Dai, Duyu Tang, Xipeng Qiu, Zenglin Xu, Shuming Shi
We present a Chinese BERT model dubbed MarkBERT that uses word information in this work.
Chinese Named Entity Recognition named-entity-recognition +7
no code implementations • 7 Mar 2022 • Fan Zhang, Duyu Tang, Yong Dai, Cong Zhou, Shuangzhi Wu, Shuming Shi
The key feature of our approach is that it is sparsely activated guided by predefined skills.
1 code implementation • ACL 2022 • Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi
We find that a frozen GPT achieves state-of-the-art performance on perfect pinyin.
no code implementations • 1 Mar 2022 • Yong Dai, Linyang Li, Cong Zhou, Zhangyin Feng, Enbo Zhao, Xipeng Qiu, Piji Li, Duyu Tang
The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters.
no code implementations • 9 May 2021 • Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu
The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.
no code implementations • EMNLP 2021 • Yanjie Gou, Yinjie Lei, Lingqiao Liu, Yong Dai, Chunxu Shen
Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context.
Ranked #2 on Task-Oriented Dialogue Systems on KVRET
no code implementations • 10 Jun 2020 • Yong Dai, Jian Liu, Xiancong Ren, Zenglin Xu
Existing algorithms of MS-UDA either only exploit the shared features, i. e., the domain-invariant information, or based on some weak assumption in NLP, e. g., smoothness assumption.
Multi-Source Unsupervised Domain Adaptation Sentiment Analysis +2