面向开放域问答的去噪表格-文本检索
Denoising Table-Text Retrieval for Open-Domain Question Answering
AI总结：
为解决表格-文本开放域问答中假阳性标签和跨表格推理证据检索困难的问题，提出DoTTeR模型，通过去噪训练集和引入表格级排序信息微调列编码器，显著提升了检索召回率与下游QA性能。
摘要：
在表格-文本开放域问答中，检索系统从表格和文本中检索相关证据以回答问题。以往在表格-文本开放域问答中的研究面临两个常见挑战：首先，它们的检索器可能会受到训练数据集中假阳性标签的影响；其次，它们可能难以针对需要跨表格推理的问题提供适当的证据。为了解决这些问题，我们提出了去噪表格-文本检索器（Denoised Table-Text Retriever，DoTTeR）。我们的方法通过假阳性检测模型测量问题相关性得分，丢弃得分较低的实例，从而利用假阳性标签更少的去噪训练数据集。随后，我们将表格级别的排序信息整合到检索器中，以协助为需要跨表格推理的问题寻找证据。为了编码这种排序信息，我们微调了一个具有排序感知能力的列编码器（rank-aware column encoder），以识别列内的最小值和最大值。实验结果表明，DoTTeR在检索召回率和下游QA任务上均显著优于强基线。我们的代码可在https://github.com/deokhk/DoTTeR获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
