Focused Meeting Summarization via Unsupervised Relation Extraction
This addresses the problem of generating concise summaries from meetings for users needing decision-focused insights, though it is incremental as it builds on prior relation extraction techniques.
The paper tackles focused meeting summarization by framing it as an unsupervised relation extraction problem, adapting an existing relation learner with task-specific constraints and features. It outperforms unsupervised baselines and a generic relation-extraction method, achieving competitive ROUGE scores with supervised methods.
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction. We adapt an existing in-domain relation learner (Chen et al., 2011) by exploiting a set of task-specific constraints and features. We evaluate the approach on a decision summarization task and show that it outperforms unsupervised utterance-level extractive summarization baselines as well as an existing generic relation-extraction-based summarization method. Moreover, our approach produces summaries competitive with those generated by supervised methods in terms of the standard ROUGE score.