Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types
This addresses the challenge of question generation for unseen data in natural language processing, though it is incremental as it builds on existing encoder-decoder architectures.
The authors tackled the problem of generating questions from knowledge base triples in a zero-shot setup, where predicates and entity types are unseen during training, and achieved a new state-of-the-art performance as shown by benchmark and human evaluations.
We present a neural model for question generation from knowledge base triples in a "Zero-Shot" setup, that is generating questions for triples containing predicates, subject types or object types that were not seen at training time. Our model leverages triples occurrences in the natural language corpus in an encoder-decoder architecture, paired with an original part-of-speech copy action mechanism to generate questions. Benchmark and human evaluation show that our model sets a new state-of-the-art for zero-shot QG.