MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization

TL;DR

MODABS introduces a multi-objective learning framework using Longformer-Encoder-Decoder for dynamic aspect-based summarization, effectively handling varying aspects and outperforming baselines across multiple datasets.

Contribution

This work presents a novel multi-objective learning approach for dynamic aspect-based summarization, enabling adaptive aspect prediction and improved summary quality.

Findings

Outperforms baseline methods on three datasets

Effectively predicts the number of aspects in summaries

Maintains high quality in single-aspect summarization

Abstract

The rapid proliferation of online content necessitates effective summarization methods, among which dynamic aspect-based summarization stands out. Unlike its traditional counterpart, which assumes a fixed set of known aspects, this approach adapts to the varied aspects of the input text. We introduce a novel multi-objective learning framework employing a Longformer-Encoder-Decoder for this task. The framework optimizes aspect number prediction, minimizes disparity between generated and reference summaries for each aspect, and maximizes dissimilarity across aspect-specific summaries. Extensive experiments show our method significantly outperforms baselines on three diverse datasets, largely due to the effective alignment of generated and reference aspect counts without sacrificing single-aspect summarization quality.