Ruiyu Fang


2023

pdf bib
Scalable-DSC: A Structural Template Prompt Approach to Scalable Dialogue State Correction
Haoxiang Su | Hongyan Xie | Hao Huang | Shuangyong Song | Ruiyu Fang | Xiaomeng Huang | Sijie Feng
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Dialogue state error correction has recently been proposed to correct wrong slot values in predicted dialogue states, thereby mitigating the error propagation problem for dialogue state tracking (DST). These approaches, though effective, are heavily intertwined with specific DST models, limiting their applicability to other DST models. To solve this problem, we propose Scalable Dialogue State Correction (Scalable-DSC), which can correct wrong slot values in the dialogue state predicted by any DST model. Specifically, we propose a Structural Template Prompt (STP) that converts predicted dialogue state from any DST models into a standardized natural language sequence as a part of the historical context, associates them with dialogue history information, and generates a corrected dialogue state sequence based on predefined template options. We further enhance Scalable-DSC by introducing two training strategies. The first employs a predictive state simulator to simulate the predicted dialogue states as the training data to enhance the generalization ability of the model. The second involves using the dialogue state predicted by DST as the training data, aiming at mitigating the inconsistent error type distribution between the training and inference. Experiments confirm that our model achieves state-of-the-art results on MultiWOZ 2.0-2.4.

pdf bib
CCL23-Eval 任务1系统报告:基于持续预训练方法与上下文增强策略的古籍命名实体识别(System Report for CCL23-Eval Task 1:Named Entity Recognition for Ancient Books based on Continual Pre-training Method and Context Augmentation Strategy)
Shiquan Wang (士权王,) | Lingling Shi (石玲玲) | Luwen Pu (蒲璐汶) | Ruiyu Fang (方瑞玉) | Yu Zhao (宇赵,) | Shuangyong Song (宋双永)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)

“本文描述了队伍“翼智团”在CCL23古籍命名实体识别评测中提交的参赛系统。该任务旨在自动识别出古籍文本中人名、书名、官职名等事件基本构成要素的重要实体,并根据使用模型参数是否大于10b分为开放赛道和封闭赛道。该任务中,我们首先利用古籍相关的领域数据和任务数据对开源预训练模型进行持续预训练和微调,显著提升了基座模型在古籍命名实体识别任务上的性能表现。其次提出了一种基于pair-wise投票的不置信实体筛选算法用来得到候选实体,并对候选实体利用上下文增强策略进行实体识别修正。在最终的评估中,我们的系统在封闭赛道中排名第二,F1得分为95.8727。”

2016

pdf bib
Automatic Identifying Entity Type in Linked Data
Qingliang Miao | Ruiyu Fang | Shuangyong Song | Zhongguang Zheng | Lu Fang | Yao Meng | Jun Sun
Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters