PAQ：6500万个可能被问到的问题和你能用它们做什么
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
摘要：
开放领域的问答模型直接利用问答（QA）对，如闭卷问答（CBQA）模型和问答对检索器，显示出承诺的速度和内存相比，传统的模型，检索和阅读文本语料库。QA对检索器还提供了可解释的答案，高度的控制，并且在测试时用新知识进行更新是微不足道的。然而，这些模型缺乏检索和阅读系统的准确性，因为相对于像维基百科这样的文本语料库，可用的QA对覆盖的知识少得多。为了促进改进的QA对模型，我们引入了可能问的问题（PAQ），这是一个非常大的65M自动生成的QA对资源。我们引入了一个新的QA对检索器，RePAQ，以补充PAQ。我们发现PAQ抢占和缓存测试问题，使RePAQ能够匹配最近的检索和读取模型的准确性，同时速度明显更快。使用PAQ，我们训练CBQA模型，其性能超过可比基线5%，但落后于RePAQ超过15%，表明显式检索的有效性。RePAQ可以配置大小（低于500MB）或速度（每秒超过1K个问题），同时保持高准确性。最后，我们展示了RePAQ在选择性QA方面的优势，当它可能不正确时，我们会放弃回答。这使得RePAQ能够“后退”到更昂贵的最先进的模型，从而形成一个比单独的最先进的模型更精确、速度快2倍的组合系统。
英文摘要：
Open-domain Question Answering models which directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared to conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models lack the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically-generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable baselines by 5%, but trail RePAQ by over 15%, indicating the effectiveness of explicit retrieval. RePAQ can be configured for size (under 500MB) or speed (over 1K questions per second) whilst retaining high accuracy. Lastly, we demonstrate RePAQ's strength at selective QA, abstaining from answering when it is likely to be incorrect. This enables RePAQ to ``back-off" to a more expensive state-of-the-art model, leading to a combined system which is both more accurate and 2x faster than the state-of-the-art model alone.
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。
