Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models

TL;DR

This paper introduces a new method for creating and evaluating domain-specific semantic models focused on accurately ranking top related words or texts, using adaptive comparisons and specialized metrics.

Contribution

It presents a novel protocol for constructing top-rank-focused evaluation datasets, new metrics for assessment, and a stochastic model to validate the dataset's effectiveness.

Findings

The dataset construction protocol improves top-rank evaluation accuracy.

New ranking metrics better capture top-rank relevance.

The stochastic model confirms the protocol's effectiveness.

Abstract

The growth of domain-specific applications of semantic models, boosted by the recent achievements of unsupervised embedding learning algorithms, demands domain-specific evaluation datasets. In many cases, content-based recommenders being a prime example, these models are required to rank words or texts according to their semantic relatedness to a given concept, with particular focus on top ranks. In this work, we give a threefold contribution to address these requirements: (i) we define a protocol for the construction, based on adaptive pairwise comparisons, of a relatedness-based evaluation dataset tailored on the available resources and optimized to be particularly accurate in top-rank evaluation; (ii) we define appropriate metrics, extensions of well-known ranking correlation coefficients, to evaluate a semantic model via the aforementioned dataset by taking into account the greater significance of top ranks. Finally, (iii) we define a stochastic transitivity model to simulate semantic-driven pairwise comparisons, which confirms the effectiveness of the proposed dataset construction protocol.