# Denoising Table-Text Retrieval for Open-Domain Question Answering

Source: [Denoising Table-Text Retrieval for Open-Domain Question Answering](<https://www.sota2.com/research/paper/68fa72b31e209131cea5804e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:57:52.846Z

Authors: Deokhyung Kang, Baikjin Jung, Yunsu Kim, Gary Geunbae Lee

Published: 2024-03-26T11:44:49.000Z

## Abstract

In table-text open-domain question answering, a retriever system retrieves relevant evidence from tables and text to answer questions. Previous studies in table-text open-domain question answering have two common challenges: firstly, their retrievers can be affected by false-positive labels in training datasets; secondly, they may struggle to provide appropriate evidence for questions that require reasoning across the table. To address these issues, we propose Denoised Table-Text Retriever (DoTTeR). Our approach involves utilizing a denoised training dataset with fewer false positive labels by discarding instances with lower question-relevance scores measured through a false positive detection model. Subsequently, we integrate table-level ranking information into the retriever to assist in finding evidence for questions that demand reasoning across the table. To encode this ranking information, we fine-tune a rank-aware column encoder to identify minimum and maximum values within a column. Experimental results demonstrate that DoTTeR significantly outperforms strong baselines on both retrieval recall and downstream QA tasks. Our code is available at https://github.com/deokhk/DoTTeR.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Table-Text Retrieval on OTT-QA (dev)](<https://www.sota2.com/research/sota/table-text-retrieval-on-ott-qa-dev.md>): Table-Text Retrieval; OTT-QA (dev); Table Recall R@1: 57.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.17611>)

[PDF](<https://arxiv.org/pdf/2403.17611.pdf>)

[Implementation](<https://github.com/deokhk/DoTTeR>)