Generating Question-Answer Hierarchies
The process of knowledge acquisition can be viewed as a question-answer game between a student and a teacher in which the student typically starts by asking broad, open-ended questions before drilling down into specifics (Hintikka, 1981; Hakkarainen and Sintonen, 2002). This pedagogical perspective motivates a new way of representing documents. In this paper, we present SQUASH (Specificity-controlled Question-Answer Hierarchies), a novel and challenging text generation task that converts an input document into a hierarchy of question-answer pairs. Users can click on high-level questions (e.g., "Why did Frodo leave the Fellowship?") to reveal related but more specific questions (e.g., "Who did Frodo leave with?"). Using a question taxonomy loosely based on Lehnert (1978), we classify questions in existing reading comprehension datasets as either "general" or "specific". We then use these labels as input to a pipelined system centered around a conditional neural language model. We extensively evaluate the quality of the generated QA hierarchies through crowdsourced experiments and report strong empirical results.
Code (2)
Tasks
Language ModelingLanguage ModellingReading ComprehensionSpecificityText GenerationSimilar Papers 제목 키워드 기반
GTM: A Generative Triple-Wise Model for Conversational Question Generation
Generating some appealing questions in open-domain conversations is an effective way to improve human-machine interactions and lead the topic to a broader or deeper direction. To avoid dull or deviated questions, some re…
DiversityQuestion GenerationQuestion-GenerationGraph Attention with Hierarchies for Multi-hop Question Answering
Multi-hop QA (Question Answering) is the task of finding the answer to a question across multiple documents. In recent years, a number of Deep Learning-based approaches have been proposed to tackle this complex task, as …
Graph AttentionGraph Neural NetworkMulti-hop Question AnsweringQuestion Answering+1Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In t…
Question AnsweringImproved Neural Relation Detection for Knowledge Base Question Answering
Relation detection is a core component for many NLP applications including Knowledge Base Question Answering (KBQA). In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning that de…
Entity LinkingKnowledge Base Question AnsweringQuestion AnsweringRelationLinguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering
Generalization on out-of-distribution (OOD) test data is an essential but underexplored topic in visual question answering. Current state-of-the-art VQA models often exploit the biased correlation between data and la…
Novel ConceptsQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)