A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization
This addresses the problem of adapting summarization models to new domains with insufficient data, but it is incremental as it builds on existing neural methods.
The study tackled domain adaptation for neural abstractive summarization by investigating transferable information, finding that pre-training on extractive summaries improves performance and combining in-domain and out-of-domain data yields better summaries when in-domain data is limited.
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.