no code implementations • EMNLP 2021 • Kewei Cheng, Ziqing Yang, Ming Zhang, Yizhou Sun
Knowledge graph inference has been studied extensively due to its wide applications.
no code implementations • 8 Feb 2024 • Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang
Some jailbreak prompt datasets, available from the Internet, can also achieve high attack success rates on many LLMs, such as ChatGLM3, GPT-3. 5, and PaLM2.
1 code implementation • 27 Jun 2023 • Zihang Xu, Ziqing Yang, Yiming Cui, Shijin Wang
IDOL achieves state-of-the-art performance on ReClor and LogiQA, the two most representative benchmarks in logical reasoning MRC, and is proven to be capable of generalizing to different pre-trained models and other types of MRC benchmarks like RACE and SQuAD 2. 0 while keeping competitive general language understanding ability through testing on tasks in GLUE.
Ranked #1 on Reading Comprehension on ReClor
5 code implementations • 17 Apr 2023 • Yiming Cui, Ziqing Yang, Xin Yao
While several large language models, such as LLaMA, have been open-sourced by the community, these predominantly focus on English corpora, limiting their usefulness for other languages.
1 code implementation • 3 Apr 2023 • Xin Yao, Ziqing Yang, Yiming Cui, Shijin Wang
In natural language processing, pre-trained language models have become essential infrastructures.
no code implementations • 9 Mar 2023 • Ziqing Yang, Zeyang Sha, Michael Backes, Yang Zhang
In this sense, we propose SeMap, a more effective mapping using the semantic alignment between the pre-trained model's knowledge and the downstream task.
1 code implementation • 15 Dec 2022 • Ziqing Yang, Yiming Cui, Xin Yao, Shijin Wang
In this work, we propose a structured pruning method GRAIN (Gradient-based Intra-attention pruning), which performs task-specific pruning with knowledge distillation and yields highly effective models.
1 code implementation • 30 Sep 2022 • Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, Yang Zhang
Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.
no code implementations • SemEval (NAACL) 2022 • Zheng Chu, Ziqing Yang, Yiming Cui, Zhigang Chen, Ming Liu
The same multi-word expressions may have different meanings in different sentences.
1 code implementation • SemEval (NAACL) 2022 • Zihang Xu, Ziqing Yang, Yiming Cui, Zhigang Chen
This paper describes our system designed for SemEval-2022 Task 8: Multilingual News Article Similarity.
no code implementations • ACL 2022 • Ziqing Yang, Yiming Cui, Zhigang Chen
Pre-trained language models have been prevailed in natural language processing and become the backbones of many NLP tasks, but the demands for computational resources have limited their applications.
1 code implementation • 14 Mar 2022 • Yiming Cui, Ziqing Yang, Ting Liu
We permute a proportion of the input text, and the training objective is to predict the position of the original token.
Ranked #4 on Stock Market Prediction on Astock
no code implementations • 28 Feb 2022 • Ziqing Yang, Yiming Cui, Zhigang Chen, Shijin Wang
In this paper, we aim to improve the multilingual model's supervised and zero-shot performance simultaneously only with the resources from supervised languages.
no code implementations • COLING 2022 • Ziqing Yang, Zihang Xu, Yiming Cui, Baoxin Wang, Min Lin, Dayong Wu, Zhigang Chen
It covers Standard Chinese, Yue Chinese, and six other ethnic minority languages.
no code implementations • Joint Conference on Lexical and Computational Semantics 2021 • Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks.
1 code implementation • EMNLP (MRQA) 2021 • Ziqing Yang, Wentao Ma, Yiming Cui, Jiani Ye, Wanxiang Che, Shijin Wang
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning.
1 code implementation • Findings (ACL) 2021 • Chenglei Si, Ziqing Yang, Yiming Cui, Wentao Ma, Ting Liu, Shijin Wang
To fill this important gap, we construct AdvRACE (Adversarial RACE), a new model-agnostic benchmark for evaluating the robustness of MRC models under four different types of adversarial attacks, including our novel distractor extraction and generation attacks.
1 code implementation • COLING 2020 • Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu
To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style Machine Reading Comprehension (SC-MRC).
1 code implementation • ACL 2020 • Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing.
no code implementations • 7 Feb 2020 • Ziqing Yang, Shoudong Han, Jun Zhao
Graph convolutional network (GCN) is now an effective tool to deal with non-Euclidean data, such as social networks in social behavior analysis, molecular structure analysis in the field of chemistry, and skeleton-based action recognition.
no code implementations • 9 Nov 2019 • Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial.
2 code implementations • 22 Jun 2019 • Weiping Song, Zhijian Duan, Ziqing Yang, Hao Zhu, Ming Zhang, Jian Tang
Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations.
Ranked #1 on Recommendation Systems on Last.FM
2 code implementations • 19 Jun 2019 • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang
To demonstrate the effectiveness of these models, we create a series of Chinese pre-trained language models as our baselines, including BERT, RoBERTa, ELECTRA, RBT, etc.