Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases

Christmann, Philipp; Roy, Rishiraj Saha; Weikum, Gerhard

doi:10.48550/arxiv.2108.08597

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main methods are Fagin algorithm and threshold algorithm, and the core task is to sort the candidates of multiple dimensions, and then calculate according to a specific pruning strategy ( Auer et al, 2008 ). For example, Christmann, Roy & Weikum (2022) fused the quantitative scores such as semantic coherence of candidate items, connectivity of knowledge graph, relevance to the question, etc., to reduce the candidate domain in knowledge question answering, and then used the threshold algorithm to filter the score list of multiple indicators to obtain the most relevant candidate neighborhood to the question. Wang et al (2021) filtered the semantically weighted scores of edges using upper and lower bound filtering and defined a star Top-k query scheme with early termination of matching.…”

Section: Related Workmentioning

confidence: 99%

Beyond top-k: knowledge reasoning for multi-answer temporal questions based on revalidation framework

Yao,

Yuan,

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

Answer sorting and filtering are two closely related steps for determining the answer to a question. Answer sorting is designed to produce an ordered list of scores based on Top-k and contextual criteria. Answer filtering optimizes the selection according to other criteria, such as the range of time constraints the user expects. However, the unclear number of answers and time constraints, as well as the high score of false positive results, indicate that the traditional sorting and selection methods cannot guarantee the quality of answers to multi-answer questions. Therefore, this study proposes MATQA, a component based on multi-answer temporal question reasoning, using a re-validation framework to convert the Top-k answer list output by the QA system into a clear number of answer combinations, and a new multi-answer based evaluation index is proposed for this output form. First, the highly correlated subgraph is selected by calculating the scores of the boot node and the related fact node. Second, the subgraph attention inference module is introduced to determine the initial answer with the highest probability. Finally, the alternative answers are clustered at the semantic level and the time constraint level. Meanwhile, the candidate answers with similar types and high scores but do not satisfy the semantic constraints or the time constraints are eliminated to ensure the number and accuracy of final answers. Experiments on the multi-answer TimeQuestions dataset demonstrate the effectiveness of the answer combinations output by MATQA.

show abstract

Section: Related Workmentioning

confidence: 99%