Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
复制标题
DOI：
10.18653/v1/p19-1261
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Yichen Jiang;Nitish Joshi;Yen-Chun Chen;Mohit Bansal
中科院分区：
文献类型：
--
作者：
Yichen Jiang;Nitish Joshi;Yen-Chun Chen;Mohit Bansal
多跳阅读理解需要模型从多个句子/文档中探索和连接相关信息，以回答关于上下文的问题。为了实现这一点，我们提出了一个可解释的3-模块系统，称为探索-建议-组装阅读器（EPAr）。首先，文档浏览器迭代地选择相关文档，并以树结构表示不同的推理链，以便吸收来自所有链的信息。答案提议器然后从推理树中的每个根到叶路径提议答案。最后，证据汇编器从每条路径中提取包含建议答案的关键句，并将它们组合起来预测最终答案。直观地说，EPAr近似于人类读者在面对多个长文档时从粗到细的理解行为。我们共同优化我们的3个模块，最大限度地减少损失的总和，从每一个阶段的条件下，前一阶段的输出。在两个多跳阅读理解数据集WikiHop和MedHop上，与最先进的模型相比，我们的EPAr模型在基线和竞争结果上取得了显着的改进。我们还提出了多个推理链恢复测试和消融研究，以证明我们的系统的能力，执行可解释的和准确的推理。
Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage’s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system’s ability to perform interpretable and accurate reasoning.