Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
By Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Oliver Wu. 2019
68 citations recorded by the source corpus.
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two general modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOTA) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.
Subfields: Artificial Intelligence, Question Answering & Reading Comprehension, Natural Language Generation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Question Answering & Reading Comprehension
Citations in the corpus
- Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering (2020, neutral): “For reference, a state-of-the-art QG model (Ma et al., 2019) trained with strong supervision achieves 49.”
- Learning to Generate Questions by Learning to Recover Answer-containing Sentences (2021, background): “Ma et al. (2020) suggested sentence-level semantic matching and answer-position-aware question generation.”