HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions
By Shaobo Li, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Chengjie Sun, Zhenzhou Ji, Bingquan Liu. 2020
36 citations recorded by the source corpus.
Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Natural Language Processing
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
In Computer Vision and Pattern Recognition
In Information Retrieval & Search
In Natural Language Processing
Citations in the corpus
- Adaptive Information Seeking for Open-Domain Question Answering (2021, methodology): “The maximum number of passages inputted into the encoders is set to 3 and the length of input tokens is limited to (Chen et al., 2017) 79.80 - IRRR †∗ (Qi et al., 2020) 84.10 ≥ 150 Asai et al., 2020) 75.70 ≥ 500 HopRetriever †∗ (Li et al., 2021) 512.”
- Answer Complex Questions: Path Ranker Is All You Need (2021, methodology): “Based on this design, Hop Retriever [17] additionally incorporates implicit entity-level relation into the hyperlinks-based retrieval stage.”
- LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs (2024, unknown): “…(Zhao et al., 2019) 51.6 QAMAT+ (Chen et al., 2023b) 57.6 HGN (Fang et al., 2019) 59.7 PathRetriever (Asai et al., 2019) 60.0 HopRetrieve (Li et al., 2021) 62.1 MDR (Xiong et al., 2020b) 62.3 HopRetrieve-plus (Li et al., 2021) 66.5 AISO (Zhu et al., 2021) 68.1 COS (Ma et al., 2023) 68.2…”