ML Anthology

DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data

Xiao Li, Yin Zhu, Sichen Liu, Jiangzhou Ju, Yuzhong Qu, Gong Cheng
AAAI 2023 pp. 13139-13147
doi:10.1609/AAAI.V37I11.26543 /aaai/2023/li2023aaai-dyrren/

Abstract

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question, state-of-the-art methods use a retriever-generator pipeline. However, their retrieval results are static, while different generation steps may rely on different sentences. To attend to the retrieved information that is relevant to each generation step, in this paper, we propose DyRRen, an extended retriever-reranker-generator framework where each generation step is enhanced by a dynamic reranking of retrieved sentences. It outperforms existing baselines on the FinQA dataset.

PDF AAAI Semantic Scholar

Cite

Text

Li et al. "DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I11.26543

Markdown

[Li et al. "DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/li2023aaai-dyrren/) doi:10.1609/AAAI.V37I11.26543

BibTeX

@inproceedings{li2023aaai-dyrren,
  title     = {{DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data}},
  author    = {Li, Xiao and Zhu, Yin and Liu, Sichen and Ju, Jiangzhou and Qu, Yuzhong and Cheng, Gong},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {13139-13147},
  doi       = {10.1609/AAAI.V37I11.26543},
  url       = {https://mlanthology.org/aaai/2023/li2023aaai-dyrren/}
}