A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization

Xinyu Hua, Lu Wang


Abstract
We study the problem of domain adaptation for neural abstractive summarization. We make initial efforts in investigating what information can be transferred to a new domain. Experimental results on news stories and opinion articles indicate that neural summarization model benefits from pre-training based on extractive summaries. We also find that the combination of in-domain and out-of-domain setup yields better summaries when in-domain data is insufficient. Further analysis shows that, the model is capable to select salient content even trained on out-of-domain data, but requires in-domain data to capture the style for a target domain.
Anthology ID:
W17-4513
Volume:
Proceedings of the Workshop on New Frontiers in Summarization
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
100–106
Language:
URL:
https://www.aclweb.org/anthology/W17-4513
DOI:
10.18653/v1/W17-4513
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-4513.pdf