Personality-dependent Neural Text Summarization
Pablo Botton da Costa, Ivandré Paraboni · 2019
In Natural Language Generation (NLG) systems, personalization strategies -i.e., the use of information about a target author to generate text that (more) closely resembles human-produced language -have long been applied to improve results.The present work addresses one such strategy -namely, the use of Big Five personality information about the target author -applied to the case of abstractive text summarization using neural sequence-tosequence models.Initial results suggest that having access to personality information does lead to more accurate (or humanlike) text summaries, and paves the way for more robust systems of this kind.