Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

event-centric summarization

Event-centric summarization is a text summarization approach in natural language processing that condenses a document by identifying, extracting, and synthesizing its core events, actions, and key participants rather than relying solely on general topic modeling or lexical frequency. Instead of treating text as an unstructured collection of sentences, this technique focuses on capturing meaningful occurrences, causal connections, and chronological developments within a narrative or informative passage. By highlighting what happened and how key actions unfold, event-centric summarization produces concise representations of central plot points and structural milestones, making it particularly effective for narrative comprehension, storyline tracking, and downstream tasks such as generating targeted, context-aware questions.

1 item

Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-centric Summarization

Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-centric Summarization

Zhenjie Zhao, Yufang Hou, Dakuo Wang, Mo Yu, Chengzhong Liu, Xiaojuan Ma

OrganizationsIBMNanjing University of Information Science and TechnologyNankai UniversityTencentThe Hong Kong University of Science and Technology

Why you should read this

Proposes a framework that pairs question type distribution learning with event-centric summarization to automatically generate high-cognitive-demand educational questions from children's storybooks.

Generating educational questions of fairytales or storybooks is vital for improving children’s literacy ability. However, it is challenging to generate questions that capture the interesting aspects of a fairytale story with educational meaningfulness. In this paper, we propose a novel question generation method that first learns the question type distribution of an input story paragraph, and then summarizes salient events which can be used to generate high-cognitive-demand questions. To train the event-centric summarizer, we fine-tune a pre-trained transformer-based sequence-to-sequence model using silver samples composed by educational question-answer pairs. On a newly proposed educational question-answering dataset FairytaleQA, we show good performance of our method on both automatic and human evaluation metrics. Our work indicates the necessity of decomposing question type distribution learning and event-centric summary generation for educational question generation.

Added

2026-10-03