融合Text-to-SQL与端到端模型，提升表格问答准确率
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
- 通过答案选择机制融合两类模型，不依赖具体模型类型
- 在含算术运算和长表时，Text-to-SQL更优；面对模糊问题则E2E更胜
- 使用特征或大模型作选择器，均显著优于单个模型
表格问答任务主要采用Text-to-SQL解析和端到端问答（E2E TQA）两种方法。尽管在多个基准上表现良好，二者尚未被系统比较，其协同潜力也未探索。本文通过评估先进模型发现：Text-to-SQL在处理含算术操作和长表的问题上更具优势；而E2E TQA在应对模糊问题、非标准表结构和复杂表内容时表现更佳。为此，我们提出一种协同表格问答方法，通过答案选择机制集成不同模型，该方法对模型类型无偏倚。实验表明，采用基于特征或大模型的答案选择器进行集成，性能显著超越单一模型。
原文摘要 · Abstract (English)
Text-to-SQL parsing and end-to-end question answering (E2E TQA) are two main approaches for Table-based Question Answering task. Despite success on multiple benchmarks, they have yet to be compared and their synergy remains unexplored. In this paper, we identify different strengths and weaknesses through evaluating state-of-the-art models on benchmark datasets: Text-to-SQL demonstrates superiority in handling questions involving arithmetic operations and long tables; E2E TQA excels in addressing ambiguous questions, non-standard table schema, and complex table contents. To combine both strengths, we propose a Synergistic Table-based Question Answering approach that integrate different models via answer selection, which is agnostic to any model types. Further experiments validate that ensembling models by either feature-based or LLM-based answer selector significantly improves the performance over individual models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。