Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study

TL;DR

This paper evaluates the challenges of Book QA by benchmarking state-of-the-art ODQA methods on the NarrativeQA dataset, revealing significant difficulties in event-centric questions and achieving a 7% improvement in Rouge-L.

Contribution

It provides a comprehensive analysis of Book QA, benchmarks current ODQA techniques on NarrativeQA, and highlights the dominance of event-centric questions as a key challenge.

Findings

Existing QA models struggle with event-oriented questions.

Benchmarking shows a 7% improvement in Rouge-L over previous state-of-the-art.

Human studies reveal the complexity of event-centric scenarios in Book QA.

Abstract

Recent advancements in open-domain question answering (ODQA), i.e., finding answers from large open-domain corpus like Wikipedia, have led to human-level performance on many datasets. However, progress in QA over book stories (Book QA) lags behind despite its similar task formulation to ODQA. This work provides a comprehensive and quantitative analysis about the difficulty of Book QA: (1) We benchmark the research on the NarrativeQA dataset with extensive experiments with cutting-edge ODQA techniques. This quantifies the challenges Book QA poses, as well as advances the published state-of-the-art with a $\sim$7\% absolute improvement on Rouge-L. (2) We further analyze the detailed challenges in Book QA through human studies.\footnote{\url{https://github.com/gorov/BookQA}.} Our findings indicate that the event-centric questions dominate this task, which exemplifies the inability of existing QA models to handle event-oriented scenarios.