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

Md Tahmid Rahman Laskar, Enamul Hoque, Jimmy Xiangji Huang


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 article, 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.
Anthology ID:
2022.cl-2.2
Volume:
Computational Linguistics, Volume 48, Issue 2 - June 2022
Month:
June
Year:
2022
Address:
Cambridge, MA
Venue:
CL
SIG:
Publisher:
MIT Press
Note:
Pages:
279–320
Language:
URL:
https://aclanthology.org/2022.cl-2.2
DOI:
10.1162/coli_a_00434
Bibkey:
Cite (ACL):
Md Tahmid Rahman Laskar, Enamul Hoque, and Jimmy Xiangji Huang. 2022. Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization. Computational Linguistics, 48(2):279–320.
Cite (Informal):
Domain Adaptation with Pre-trained Transformers for Query-Focused Abstractive Text Summarization (Laskar et al., CL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.cl-2.2.pdf
Code
 tahmedge/preqfas
Data
CNN/Daily MailMEDIQA-AnSTrecQAWikiQA