Improving Correlation with Human Judgments by Integrating Semantic Similarity with Second--Order Vectors
This work addresses the need for more accurate semantic measures in natural language processing, particularly for biomedical applications, though it is incremental as it builds on existing vector space methods.
The paper tackled the problem of improving semantic similarity and relatedness measures by integrating human-curated taxonomy-based similarity into second-order vector representations, resulting in enhanced correlation with human judgments compared to existing word embedding methods.
Vector space methods that measure semantic similarity and relatedness often rely on distributional information such as co--occurrence frequencies or statistical measures of association to weight the importance of particular co--occurrences. In this paper, we extend these methods by incorporating a measure of semantic similarity based on a human curated taxonomy into a second--order vector representation. This results in a measure of semantic relatedness that combines both the contextual information available in a corpus--based vector space representation with the semantic knowledge found in a biomedical ontology. Our results show that incorporating semantic similarity into a second order co--occurrence matrices improves correlation with human judgments for both similarity and relatedness, and that our method compares favorably to various different word embedding methods that have recently been evaluated on the same reference standards we have used.