Challenges in Domain-Specific Abstractive Summarization and How to Overcome them

Abstract

Large Language Models work quite well with general-purpose data and many tasks in Natural Language Processing. However, they show several limitations when used for a task such as domain-specific abstractive text summarization. This paper identifies three of those limitations as research problems in the context of abstractive text summarization: 1) Quadratic complexity of transformer-based models with respect to the input text length; 2) Model Hallucination, which is a model's ability to generate factually incorrect text; and 3) Domain Shift, which happens when the distribution of the model's training and test corpus is not the same. Along with a discussion of the open research questions, this paper also provides an assessment of existing state-of-the-art techniques relevant to domain-specific text summarization to address the research gaps.

References in corpus (8)

• BERTScore: Evaluating Text Generation with BERT
• Longformer: The Long-Document Transformer
• PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
• Efficient Transformers: A Survey
• The Reversible Residual Network: Backpropagation Without Storing Activations
• Assessing The Factual Accuracy of Generated Text
• The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey
• Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization