Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarization

TL;DR

This paper leverages pre-trained transformer models with domain adaptation techniques to improve query-focused abstractive summarization, achieving state-of-the-art results across multiple datasets.

Contribution

It introduces a novel application of transfer learning, weak supervision, and distant supervision for domain adaptation in QFTS using pre-trained transformers.

Findings

Effective domain adaptation techniques improve summarization quality.

Achieved new state-of-the-art results on six datasets.

Demonstrated the versatility of transformer models in QFTS.

Abstract

The Query Focused Text Summarization (QFTS) task aims at building systems that generate the summary of the text document(s) based on the given query. A key challenge in addressing this task is the lack of large labeled data for training the summarization model. In this paper, we address this challenge by exploring a series of domain adaptation techniques. Given the recent success of pre-trained transformer models in a wide range of natural language processing tasks, we utilize such models to generate abstractive summaries for the QFTS task for both single-document and multi-document scenarios. For domain adaptation, we apply a variety of techniques using pre-trained transformer-based summarization models including transfer learning, weakly supervised learning, and distant supervision. Extensive experiments on six datasets show that our proposed approach is very effective in generating abstractive summaries for the QFTS task while setting a new state-of-the-art result in several datasets across a set of automatic and human evaluation metrics.