Li Zeng
2024
DRAMA: Dynamic Multi-Granularity Graph Estimate Retrieval over Tabular and Textual Question Answering
Ruize Yuan
|
Xiang Ao
|
Li Zeng
|
Qing He
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
The TableTextQA task requires finding the answer to the question from a combination of tabular and textual data, which has been gaining increasing attention. The row-based approaches have demonstrated remarkable effectiveness. However, they suffer from the following limitations: (1) a lack of interaction between rows; (2) excessively long input lengths; and (3) question attention shifts in the multi-hop QA task. To this end, we propose a novel method: Dynamic Multi-Granularity Graph Estimate Retrieval - DRAMA. Our method incorporates an interaction mechanism among multiple rows. Specifically, we utilize a memory bank to store the features of each row, thereby facilitating the construction of a heterogeneous graph with multi-row information. Besides, a Dynamic Graph Attention Network (DGAT) module is engaged to gauge the attention shift in the multi-hop question and eliminate the noise information dynamically. Empirical results on the widely used HybridQA and TabFact datasets demonstrate that the proposed model is effective.
2023
BIT-ACT: An Ancient Chinese Translation System Using Data Augmentation
Li Zeng
|
Yanzhi Tian
|
Yingyu Shan
|
Yuhang Guo
Proceedings of ALT2023: Ancient Language Translation Workshop
This paper describes a translation model for ancient Chinese to modern Chinese and English for the Evahan 2023 competition, a subtask of the Ancient Language Translation 2023 challenge. During the training of our model, we applied various data augmentation techniques and used SiKu-RoBERTa as part of our model architecture. The results indicate that back translation improves the model’s performance, but double back translation introduces noise and harms the model’s performance. Fine-tuning on the original dataset can be helpful in solving the issue.
Search
Co-authors
- Ruize Yuan 1
- Xiang Ao 1
- Qing He 1
- Yanzhi Tian 1
- Yingyu Shan 1
- show all...