RikiNet: Reading Wikipedia Pages for Natural Question Answering
By Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Nan Duan. 2020
59 citations recorded by the source corpus.
Reading long documents to answer open-domain questions remains challenging in natural language understanding. In this paper, we introduce a new model, called RikiNet, which reads Wikipedia pages for natural question answering. RikiNet contains a dynamic paragraph dual-attention reader and a multi-level cascaded answer predictor. The reader dynamically represents the document and question by utilizing a set of complementary attention mechanisms. The representations are then fed into the predictor to obtain the span of the short answer, the paragraph of the long answer, and the answer type in a cascaded manner. On the Natural Questions (NQ) dataset, a single RikiNet achieves 74.3 F1 and 57.9 F1 on long-answer and short-answer tasks. To our best knowledge, it is the first single model that outperforms the single human performance. Furthermore, an ensemble RikiNet obtains 76.1 F1 and 61.3 F1 on long-answer and short-answer tasks, achieving the best performance on the official NQ leaderboard.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Noah A. Smith
- Matt Gardner
- Hannaneh Hajishirzi
- Iz Beltagy
- J. Ainslie
- Luke S. Zettlemoyer
- Arman Cohan
- Jonathan Berant
In Computer Vision and Pattern Recognition
- Matt Gardner
- Noah A. Smith
- J. Ainslie
- Anirudh Ravula
- Li Yang
- Chris Alberti
- Sumit K. Sanghai
- Santiago Ontañón
Citations in the corpus
- Big Bird: Transformers for Longer Sequences (2020, neutral): “[62] D.”
- ETC: Encoding Long and Structured Inputs in Transformers (2020, methodology): “The first three rows show baseline models: BERTbase, BERT-large, and RikiNet (Liu et al., 2020) (one of the best models in the NQ leaderboard).”
- A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers (2021, background): “, 2020) have led to significant progress in reading at scale (e.g., Asai et al., 2020; Guu et al., 2020; Liu et al., 2020).”