Exploiting Explicit Paths for Multi-hop Reading Comprehension
This addresses the problem of multi-hop reasoning in reading comprehension for NLP systems, offering an incremental improvement with explicit path explanations.
The paper tackles multi-hop reading comprehension by proposing PathNet, a path-based reasoning approach that generates and scores potential paths through passages without direct supervision. The model outperforms prior models on the Wikihop dataset and matches state-of-the-art performance on OpenBookQA.
We propose a novel, path-based reasoning approach for the multi-hop reading comprehension task where a system needs to combine facts from multiple passages to answer a question. Although inspired by multi-hop reasoning over knowledge graphs, our proposed approach operates directly over unstructured text. It generates potential paths through passages and scores them without any direct path supervision. The proposed model, named PathNet, attempts to extract implicit relations from text through entity pair representations, and compose them to encode each path. To capture additional context, PathNet also composes the passage representations along each path to compute a passage-based representation. Unlike previous approaches, our model is then able to explain its reasoning via these explicit paths through the passages. We show that our approach outperforms prior models on the multi-hop Wikihop dataset, and also can be generalized to apply to the OpenBookQA dataset, matching state-of-the-art performance.