Predicting Relevance Scores for Triples from Type-Like Relations using Neural Embedding - The Cabbage Triple Scorer at WSDM Cup 2017
This work addresses the need for accurate triple scoring in entity search, but it is incremental as it applies neural embeddings to a specific competition task without introducing a new paradigm.
The paper tackled the problem of predicting relevance scores for triples from type-like relations, which is crucial for ranking in entity search, by proposing a neural embedding method that achieved top performance with an accuracy of 0.74, average score difference of 1.74, and average Kendall's Tau of 0.35 in the WSDM Cup 2017 challenge.
The WSDM Cup 2017 Triple scoring challenge is aimed at calculating and assigning relevance scores for triples from type-like relations. Such scores are a fundamental ingredient for ranking results in entity search. In this paper, we propose a method that uses neural embedding techniques to accurately calculate an entity score for a triple based on its nearest neighbor. We strive to develop a new latent semantic model with a deep structure that captures the semantic and syntactic relations between words. Our method has been ranked among the top performers with accuracy - 0.74, average score difference - 1.74, and average Kendall's Tau - 0.35.