Papers by Karel Ondrej
R2-D2: A Modular Baseline for Open-Domain Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Using extractive and generative reader, we demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA. |
| Approach: | They propose a four-stage open-domain QA pipeline with a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system’s components. |
| Outcome: | The proposed pipeline outperforms state-of-the-art on three open-domain QA datasets and is twice as effective as the posterior averaging ensemble of the same models with different parameters. |