Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

By Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, Bowen Zhou. 2019

156 citations recorded by the source corpus.

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In this paper, we propose an effective and interpretable Select, Answer and Explain (SAE) system to solve the multi-document RC problem. Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information. This is achieved by a document classifier trained with a novel pairwise learning-to-rank loss. The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences. The model is optimized with a multi-task learning objective on both token level for answer prediction and sentence level for supporting sentences prediction, together with an attention-based interaction between these two tasks. Evaluated on HotpotQA, a challenging multi-hop RC data set, the proposed SAE system achieves top competitive performance in distractor setting compared to other existing systems on the leaderboard.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Information Retrieval & Search, 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 Information Systems

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Longformer: The Long-Document Transformer (2020, background): “Note that both approaches are signiﬁcantly simpler than recent SOTA models that include pipeline approaches of multiple stages and customized architectures (e.g., (Tu et al., 2019; Chen et al., 2019; Tu et al., 2020; Groeneveld et al., 2020)).”
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models (2021, methodology): “While many multi-hop QA models exist for HotpotQA and DROP, these are often equally complex models (Tu et al., 2020; Fang et al., 2020; Ran et al., 2019) focusing on just one of these datasets.”
Pre-trained models for natural language processing: A survey (2020, background): “[182] proposed an interpretable “Select, Answer, and Explain” (SAE) system that PTM acts as the encoder in the selection module.”
Hierarchical Graph Network for Multi-hop Question Answering (2019, background): “48 SAE-large (Tu et al., 2020) 66.”
Multi-hop Question Answering via Reasoning Chains (2019, neutral): “DecompRC (Min et al., 2019b) 55.20 69.63 N QFE (Nishida et al., 2019) 53.86 68.06 Y DFGN (Qiu et al., 2019) 56.31 69.69 Y HGN (Fang et al., 2019) 66.07 79.36 Y SAE (Tu et al., 2019a) 66”
Is Graph Structure Necessary for Multi-hop Question Answering? (2020, background): “…(Nishida et al., 2019) 34.63 59.61 DFGN (Qiu et al., 2019) 33.62 59.82 TAP2 (Glass et al., 2019) 39.77 69.12 HGN (Fang et al., 2019) 43.57 71.03 SAE (Tu et al., 2019a) 45 eral extra modules in the graph fusion block, including query-entity attention, query update mechanism, and weak supervision.”
CogLTX: Applying BERT to Long Texts (2020, unknown): “The thought of SAE [45] Ablation studies.”
♫ MuSiQue: Multihop Questions via Single-hop Question Composition (2021, methodology): “This model, inspired by Quark (Groeneveld et al., 2020) and SAE (Tu et al., 2020), has two parts.”
Exploiting Reasoning Chains for Multi-hop Science Question Answering (2021, methodology): “…AristoRoBERTa (AllenAI, 2019), KF-SIR (Banerjee and Baral, 2020), FreeLB (Zhu et al., 2020), DPR (Karpukhin et al., 2020), AMR-SG (Xu et al., 2021) and another two methods leveraging on an additional knowledge graph (Speer et al., 2017): PG (Wang et al., 2020), and MHGRN (Feng et al., 2020).”
Trustworthy AI: From Principles to Practices (2021, methodology): “For deep learning models like the Convolutional Neural Network (CNN) or the transformer, the inspection of intermediate features is a widely used means of explaining model behavior [332, 366].”
Is Graph Structure Necessary for Multi-hop Reasoning? (2020, unknown): “Tu et al. (2019b) extended the entity graph to a heterogeneous graph by introducing document nodes and query nodes.”
Graph Sequential Network for Reasoning over Sequences (2020, methodology): “Since the point of our paper is to show the efﬁcacy of the proposed GSN model, we only show results on development set; getting numbers on test set requires several other modules (Xiao et al., 2019; Tu et al., 2019a) that are unrelated to our proposed GSN.”
F1 Is Not Enough! Models and Evaluation towards User-Centered Explainable Question Answering (2020, background): “Other approaches are based on question decomposition (Min et al., 2019; Perez et al., 2020), graph/hierarchical structures (Tu et al., 2019; Fang et al., 2019; Asai et al., 2020), virtual knowledge bases (Dhingra et al., 2020) or transformer models (Zhao et al., 2020).”
A Simple Yet Strong Pipeline for HotpotQA (2020, background): “86 SAE (Tu et al., 2020) 61.”