Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

By Yichen Jiang, Nitish Joshi, Yen-Chun Chen, Mohit Bansal. 2019

42 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Measuring Association Between Labels and Free-Text Rationales (2020, background): “One way towards faithfulness is to introduce architectural modiﬁcations or constraints that produce rationales with desirable properties (Andreas et al., 2016; Schwartz et al., 2018; Jiang et al., 2019, inter alia ).”
Multi-hop Question Answering via Reasoning Chains (2019, background): “This represents a step towards building models that represent the reasoning process more explicitly (Trivedi et al., 2019; Jiang et al., 2019).”
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference (2020, background): “Interpretability Interpretability is an important line of research recently (Jiang et al., 2019; Sydorova et al., 2019; Asai et al., 2020).”
A Survey of the State of Explainable AI for Natural Language Processing (2020, methodology): “…natural language explanation for a QA system (Abujabal et al., 2017). tion techniques, such as using raw examples to present example-driven approaches (Jiang et al., 2019; Croce et al., 2019) (e.g., Figure 1e), and dependency parse trees to represent input questions (Abujabal et al., 2017).”
Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network (2020, unknown): “…BAG [Cao et al., 2019], HDE [Tu et al., 2019], MHQA-GRN [Song et al., 2018]), memory-based approaches (Coref-GRU [Dhingra et al., 2018], EPAr [Jiang et al., 2019]), path-based approaches (PathNet [Kundu et al., 2019]), and attention-based approaches (CFC [Zhong et al., 2019], DynSAN [Zhuang…”