VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation

ACL ARR 2025 July Submission1361 Authors

Abstract:

Multi-hop Question Generation (QG) effectively evaluates reasoning but remains confined to text; Video Question Generation (VideoQG) is limited to zero-hop questions over single segments.
To address this, we introduce VideoChain, a novel Multi-hop Video Question Generation (MVQG) framework designed to generate questions that require reasoning across multiple, temporally separated video segments. VideoChain features a modular architecture built on a modified BART backbone enhanced with video embeddings, capturing textual and visual dependencies.Using the TVQA+ dataset, we automatically construct the large-scale MVQ-60 dataset by merging zero-hop QA pairs, ensuring scalability and diversity. Evaluations show VideoChain strong performance across standard generation metrics: ROUGE-L (0.6454), ROUGE-1 (0.6854), BLEU-1 (0.6711), BERTScore-F1 (0.7967), and semantic similarity (0.8110).These results highlight the model’s ability to generate coherent, contextually grounded, and reasoning-intensive questions.
To facilitate future research, we publicly release our code and dataset https://anonymous.4open.science/r/VideoChain-7ED9.

Paper Type: Long

Research Area: Question Answering

Research Area Keywords: Video Question Answering, Multi Hop Question Answering, Natural Language Processing

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 1361