论文标题
仅在指甲上使用锤子：一种用于检索问答证据的混合方法
Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering
论文作者
论文摘要
证据检索是可解释的问题回答（QA）的关键组成部分。我们认为，尽管最近取得了进展，但基于变压器网络的方法（例如通用句子编码器（USE-QA））并不总是胜过传统信息检索（IR）方法，例如BM25，用于质量检查的证据检索。我们介绍了一个词汇探测任务，该任务验证了这一观察结果：我们证明了神经IR方法具有捕获问题和答案之间词汇差异的能力，但是错过了明显的词汇重叠信号。从此探测分析中学习，我们引入了一种混合方法，以检索证据检索，从而结合了两个IR方向的优势。我们的方法使用路由分类器，该分类器何时将传入的问题直接到BM25与使用-QA进行证据检索使用非常简单的统计数据，可以从BM25模型产生的顶级候选证据句子中有效提取。我们证明，该混合证据检索通常比在三个QA数据集上的单个检索策略（OpenBookQa，Reqa Squad和Reqa nq）上的表现更好。此外，我们表明，所提出的路由策略比神经方法快得多，其运行时的速度比USE-QA快5倍。
Evidence retrieval is a key component of explainable question answering (QA). We argue that, despite recent progress, transformer network-based approaches such as universal sentence encoder (USE-QA) do not always outperform traditional information retrieval (IR) methods such as BM25 for evidence retrieval for QA. We introduce a lexical probing task that validates this observation: we demonstrate that neural IR methods have the capacity to capture lexical differences between questions and answers, but miss obvious lexical overlap signal. Learning from this probing analysis, we introduce a hybrid approach for evidence retrieval that combines the advantages of both IR directions. Our approach uses a routing classifier that learns when to direct incoming questions to BM25 vs. USE-QA for evidence retrieval using very simple statistics, which can be efficiently extracted from the top candidate evidence sentences produced by a BM25 model. We demonstrate that this hybrid evidence retrieval generally performs better than either individual retrieval strategy on three QA datasets: OpenBookQA, ReQA SQuAD, and ReQA NQ. Furthermore, we show that the proposed routing strategy is considerably faster than neural methods, with a runtime that is up to 5 times faster than USE-QA.
