论文标题
无监督的问题分解问题回答
Unsupervised Question Decomposition for Question Answering
论文作者
论文摘要
我们旨在通过将硬问题分解为现有质量检查系统能够回答的更简单的子问题来改善问题答案（QA）。由于用分解标记问题很麻烦，因此我们采用一种无监督的方法来产生子问题，还使我们能够利用互联网中的数百万个问题。具体而言，我们为一到N无监督的序列转导（ONUS）提出了一种算法，该算法学会将一个硬的多跳问题映射到许多简单的单跳子问题上。我们使用现成的质量检查模型回答子问题，并将其结合到最终答案中的重新组合模型的结果答案。我们在HotPotQA上显示了对原始，室外和多跳开发套件的强大基线的大量质量检查改进。 Onus会自动学习分解各种问题，同时匹配质量检查的监督和启发式分解方法的实用性，并在流利度中超过这些方法。定性地，我们发现使用子问题有望阐明QA系统为何进行预测。
We aim to improve question answering (QA) by decomposing hard questions into simpler sub-questions that existing QA systems are capable of answering. Since labeling questions with decompositions is cumbersome, we take an unsupervised approach to produce sub-questions, also enabling us to leverage millions of questions from the internet. Specifically, we propose an algorithm for One-to-N Unsupervised Sequence transduction (ONUS) that learns to map one hard, multi-hop question to many simpler, single-hop sub-questions. We answer sub-questions with an off-the-shelf QA model and give the resulting answers to a recomposition model that combines them into a final answer. We show large QA improvements on HotpotQA over a strong baseline on the original, out-of-domain, and multi-hop dev sets. ONUS automatically learns to decompose different kinds of questions, while matching the utility of supervised and heuristic decomposition methods for QA and exceeding those methods in fluency. Qualitatively, we find that using sub-questions is promising for shedding light on why a QA system makes a prediction.
