Incorporating Phrases in Latent Query Reformulation for Multi-Hop Question Answering

Jiuyang Tang, Shengze Hu, Ziyang Chen, Hao Xu and Zhen Tan
Additional contact information
Jiuyang Tang: Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
Shengze Hu: Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
Ziyang Chen: Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
Hao Xu: Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
Zhen Tan: Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China

Mathematics, 2022, vol. 10, issue 4, 1-14

Abstract: In multi-hop question answering (MH-QA), the machine needs to infer the answer to a given question from multiple documents. Existing models usually apply entities as basic units in the reasoning path. Then they use relevant entities (in the same sentence or document) to expand the path and update the information of these entities to finish the QA. The process might add an entity irrelevant to the answer to the graph and then lead to incorrect predictions. It is further observed that state-of-the-art methods are susceptible to reasoning chains that pivot on compound entities. To make up the deficiency, we present a viable solution, i.e., incorporate phrases in the latent query reformulation method (IP-LQR), which incorporates phrases in the latent query reformulation to improve the cognitive ability of the proposed method for multi-hop question answering. Specifically, IP-LQR utilizes information from relevant contexts to reformulate the question in the semantic space. Then the updated query representations interact with contexts within which the answer is hidden. We also design a semantic-augmented fusion method based on the phrase graph, which is then used to propagate the information. IP-LQR is empirically evaluated on a popular MH-QA benchmark, HotpotQA, and the results of IP-LQR consistently outperform those of the state of the art, verifying its superiority. In summary, by incorporating phrases in the latent query reformulation and employing semantic-augmented embedding fusion, our proposed model can lead to better performance on MH-QA.

Keywords: multiple documents; multi-hop question answering; phrase incorporation; latent query reformulation (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/4/646/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/4/646/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:4:p:646-:d:753287

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().