End-to-End Table Question Answering via Retrieval-Augmented Generation
Author
Pan, FeiFei; Canim, Mustafa; Glass, Michael; Gliozzo, Alfio; Hendler, James A.Other Contributors
Date Issued
2022-03Degree
Terms of Use
Attribution-NonCommercial-NoDerivs 3.0 United StatesFull Citation
Feifei Pan, Mustafa Canim, Michael Glass, Alfio Gliozzo, and James Hendler. "End-to-End Table Question Answering via Retrieval-Augmented Generation." arXiv preprint arXiv:2203.16714 March 2022Metadata
Show full item recordAbstract
Most existing end-to-end Table Question Answering (Table QA) models consist of a two-stage framework with a retriever to select relevant table candidates from a corpus and a reader to locate the correct answers from table candidates. Even though the accuracy of the reader models is significantly improved with the recent transformer-based approaches, the overall performance of such frameworks still suffers from the poor accuracy of using traditional information retrieval techniques as retrievers. To alleviate this problem, we introduce T-RAG, an end-to-end Table QA model, where a non-parametric dense vector index is fine-tuned jointly with BART, a parametric sequence-to-sequence model to generate answer tokens. Given any natural language question, T-RAG utilizes a unified pipeline to automatically search through a table corpus to directly locate the correct answer from the table cells. We apply T-RAG to recent open-domain Table QA benchmarks and demonstrate that the fine-tuned T-RAG model is able to achieve state-of-the-art performance in both the end-to-end Table QA and the table retrieval tasks.;Department
Publisher
arXivRelationships
Access
Collections
The following license files are associated with this item: