Analyzing Multi-Task Learning for Abstractive Text Summarization

Abstract

Despite the recent success of multi-task learning and pre-finetuning for natural language understanding, few works have studied the effects of task families on abstractive text summarization. Task families are a form of task grouping during the pre-finetuning stage to learn common skills, such as reading comprehension. To close this gap, we analyze the influence of multi-task learning strategies using task families for the English abstractive text summarization task. We group tasks into one of three strategies, i.e., sequential, simultaneous, and continual multi-task learning, and evaluate trained models through two downstream tasks. We find that certain combinations of task families (e.g., advanced reading comprehension and natural language inference) positively impact downstream performance. Further, we find that choice and combinations of task families influence downstream performance more than the training scheme, supporting the use of task families for abstractive text summarization.

References in corpus (8)

• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• Continual Lifelong Learning in Natural Language Processing: A Survey
• Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts
• The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey
• CTRLsum: Towards Generic Controllable Text Summarization
• Identifying Machine-Paraphrased Plagiarism
• Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles
• Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection