Improving Neural Question Generation using World Knowledge
This work addresses the challenge of generating more natural questions for natural language processing applications, but it is incremental as it builds on existing neural question generation models.
The paper tackled the problem of generating human-like questions from text by incorporating world knowledge (linked entities and fine-grained entity types) into a neural model, resulting in improvements of 1.37 and 1.59 absolute BLEU 4 scores on SQuAD and MS MARCO datasets, respectively.
In this paper, we propose a method for incorporating world knowledge (linked entities and fine-grained entity types) into a neural question generation model. This world knowledge helps to encode additional information related to the entities present in the passage required to generate human-like questions. We evaluate our models on both SQuAD and MS MARCO to demonstrate the usefulness of the world knowledge features. The proposed world knowledge enriched question generation model is able to outperform the vanilla neural question generation model by 1.37 and 1.59 absolute BLEU 4 score on SQuAD and MS MARCO test dataset respectively.