Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarization
This addresses the data scarcity problem for researchers and practitioners in natural language processing working on query-focused summarization, though it is incremental as it builds on existing transformer models.
The paper tackled the lack of large labeled data for Query Focused Text Summarization (QFTS) by applying domain adaptation techniques with pre-trained transformers, achieving new state-of-the-art results on several datasets in both single-document and multi-document scenarios.
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.