Inferring the semantic relationships of words within an ontology using random indexing: applications to pharmacogenomics

Abstract

The biomedical literature presents a uniquely challenging text mining problem. Sentences are long and complex, the subject matter is highly specialized with a distinct vocabulary, and producing annotated training data for this domain is time consuming and expensive. In this environment, unsupervised text mining methods that do not rely on annotated training data are valuable. Here we investigate the use of random indexing, an automated method for producing vector-space semantic representations of words from large, unlabeled corpora, to address the problem of term normalization in sentences describing drugs and genes. We show that random indexing produces similarity scores that capture some of the structure of PHARE, a manually curated ontology of pharmacogenomics concepts. We further show that random indexing can be used to identify likely word candidates for inclusion in the ontology, and can help localize these new labels among classes and roles within the ontology.

Figure 1:

An example of relation normalization using PHARE. Here two sentences that look very different on the surface are mapped to the same normalized “fact”.

Figure 2.

Bar plots of correlations between number of common parents in ontology and distributional similarity scores for (left) concepts and (right) roles. Each bar represents a different type of semantic vector. Orange bars represent vectors with width 1, gray width 3, and blue width 5.

Figure 3.

Correct concepts/roles found, by position in the ranked list. Separate graphs are shown for (left) roles and (right) concepts. The total number of concepts included here was 228 and the total number of roles was 54.

Figure 4.

Dependency parses for the two example sentences shown in Figure 1. Because the structure of these sentences is so similar, one could conceive of using distributional semantics methods to establish an alignment between them, thus performing a task akin to normalization without the use of an ontology.