Fact-driven Logical Reasoning for Machine Reading Comprehension
This work addresses the challenge of enhancing reasoning ability in machines for reading comprehension tasks, particularly where temporary knowledge is crucial, representing an incremental advancement by extending existing clue-based methods.
The paper tackles the problem of logical reasoning in machine reading comprehension by addressing the insufficiency of entity-aware clues for tasks requiring temporary facts or events, proposing a hierarchical approach that covers both commonsense and temporary knowledge clues. The result shows substantial improvements over baselines on logical reasoning benchmarks and dialogue modeling datasets, with the approach being general across backbone models.
Recent years have witnessed an increasing interest in training machines with reasoning ability, which deeply relies on accurately and clearly presented clue forms. The clues are usually modeled as entity-aware knowledge in existing studies. However, those entity-aware clues are primarily focused on commonsense, making them insufficient for tasks that require knowledge of temporary facts or events, particularly in logical reasoning for reading comprehension. To address this challenge, we are motivated to cover both commonsense and temporary knowledge clues hierarchically. Specifically, we propose a general formalism of knowledge units by extracting backbone constituents of the sentence, such as the subject-verb-object formed ``facts''. We then construct a supergraph on top of the fact units, allowing for the benefit of sentence-level (relations among fact groups) and entity-level interactions (concepts or actions inside a fact). Experimental results on logical reasoning benchmarks and dialogue modeling datasets show that our approach improves the baselines substantially, and it is general across backbone models. Code is available at \url{https://github.com/ozyyshr/FocalReasoner}.