# RikiNet: Reading Wikipedia Pages for Natural Question Answering

arXiv: https://arxiv.org/abs/2004.14560 · HTML: https://mlsanity.com/paper/2004.14560/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 21 of 21)

- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [Adversarial Retriever-Ranker for dense text retrieval](https://mlsanity.com/paper/2110.03611/) (2021)
- [Poolingformer: Long Document Modeling with Pooling Attention](https://mlsanity.com/paper/2105.04371/) (2021)
- [SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining](https://mlsanity.com/paper/2108.08983/) (2021)
- [Representations for Question Answering from Documents with Tables and Text](https://mlsanity.com/paper/2101.10573/) (2021)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Generative Dense Retrieval: Memory Can Be a Burden](https://mlsanity.com/paper/2401.10487/) (2024)
- [BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles](https://mlsanity.com/paper/2109.11087/) (2021)
- [DyRRen: A Dynamic Retriever-Reranker-Generator Model for Numerical Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2211.12668/) (2022)
- [Clues Before Answers: Generation-Enhanced Multiple-Choice QA](https://mlsanity.com/paper/2205.00274/) (2022)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Synthetic Target Domain Supervision for Open Retrieval QA](https://mlsanity.com/paper/2204.09248/) (2022)
- [Instilling Type Knowledge in Language Models via Multi-Task QA](https://mlsanity.com/paper/2204.13796/) (2022)
- [When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions](https://mlsanity.com/paper/2108.13875/) (2021)
- [Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems](https://mlsanity.com/paper/2201.05767/) (2022)
- [Sentence Representations via Gaussian Embedding](https://mlsanity.com/paper/2305.12990/) (2023)
- [MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering](https://mlsanity.com/paper/2310.06436/) (2023)
- [VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension](https://mlsanity.com/paper/2105.03229/) (2021)
- [A Quantitative Review on Language Model Efficiency Research](https://mlsanity.com/paper/2306.01768/) (2023)
- [Interpreting Answers to Yes-No Questions in User-Generated Content](https://mlsanity.com/paper/2310.15464/) (2023)

## Abstract (arXiv)

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