Papers with retriever-reader model
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to open-domain question answering struggle to retrieve indirectly related evidence when no direct evidence is provided. |
| Approach: | They propose a retriever-reader model that learns to attend on essential terms during the question answering process. |
| Outcome: | The proposed model achieves the state-of-the-art on multiple open-domain QA datasets and achieves a 'reader-reader' level. |
UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering (2022.findings-naacl)
Copied to clipboard
Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih
| Challenge: | a recent study aims to answer factual questions using a structured knowledge base (KBQA). |
| Approach: | They propose a unifying approach that homogenizes all knowledge sources by reducing them to text . they demonstrate that UniK-QA is a simple and yet effective way to combine heterogeneous sources of knowledge. |
| Outcome: | The proposed approach improves state-of-the-art results on knowledge-base QA tasks by 11 points compared to graph-based methods. |