1 Hit in 1.8 sec

VOGUE: Answer Verbalization through Multi-Task Learning [article]

Endri Kacupaj, Shyamnath Premnadh, Kuldeep Singh, Jens Lehmann, Maria Maleshkova
2021 arXiv   pre-print
.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs.  ...  We evaluate our framework on existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and METEOR scores.  ...  The dataset consists of 5042 entities and 615 relations. • ParaQA (Kacupaj et al., 2021a) is a QA dataset with multiple paraphrased responses.  ... 
arXiv:2106.13316v2 fatcat:4nvt3gtje5dsfcqabhmms44vge