A Recurrent BERT-based Model for Question Generation
By Ying-Hong Chan, Yao-Chung Fan. 2019
156 citations recorded by the source corpus.
In this study, we investigate the employment of the pre-trained BERT language model to tackle question generation tasks. We introduce three neural architectures built on top of BERT for question generation tasks. The first one is a straightforward BERT employment, which reveals the defects of directly using BERT for text generation. Accordingly, we propose another two models by restructuring our BERT employment into a sequential manner for taking information from previous decoded results. Our models are trained and evaluated on the recent question-answering dataset SQuAD. Experiment results show that our best model yields state-of-the-art performance which advances the BLEU 4 score of the existing best models from 16.85 to 22.17.
Subfields: Artificial Intelligence, Natural Language Processing, Question Answering & Reading Comprehension
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
- Cordelia Schmid
- Ivan Laptev
- Josef Sivic
- Antoine Miech
- Andrew Zisserman
- Luc Van Gool
- Bernt Schiele
- Limin Wang
In Natural Language Processing
- Ivan Laptev
- Antoine Miech
- Motoaki Kawanabe
- Josef Sivic
- Antoine Yang
- Taiki Miyanishi
- Shuhei Kurita
- Cordelia Schmid
In Question Answering & Reading Comprehension
- Ivan Laptev
- Motoaki Kawanabe
- Josef Sivic
- Antoine Miech
- Antoine Yang
- Taiki Miyanishi
- Shuhei Kurita
- Cordelia Schmid
Citations in the corpus
- Just Ask: Learning to Answer Questions from Millions of Narrated Videos (2020, positive): “We follow [4, 14, 54] and use the weights available at [3] trained for answer span extraction and answer-aware question generation, respectively, on SQuADv1 [65].”
- ScanQA: 3D Question Answering for Spatial Scene Understanding (2021, methodology): “The ScanQA dataset was created in multiple phrases: automatic QA generation [2, 8, 30, 46], question filtering, question editing, and answer collection.”