Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
This addresses the challenge of efficiently finding and reasoning over multiple text sources for complex questions, though it is incremental as it builds on existing retrieval-based QA methods.
The paper tackles multi-hop open-domain question answering by developing a method to iteratively retrieve supporting paragraphs from a large knowledge base, achieving state-of-the-art performance on SQuAD-Open and HotpotQA datasets.
This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. We present a method for retrieving multiple supporting paragraphs, nested amidst a large knowledge base, which contain the necessary evidence to answer a given question. Our method iteratively retrieves supporting paragraphs by forming a joint vector representation of both a question and a paragraph. The retrieval is performed by considering contextualized sentence-level representations of the paragraphs in the knowledge source. Our method achieves state-of-the-art performance over two well-known datasets, SQuAD-Open and HotpotQA, which serve as our single- and multi-hop open-domain QA benchmarks, respectively.