Comparison of vector space model methodologies to reconcile cross-species neuroanatomical concepts.

TLDR: Results indicate that the NTAR system could assist neuroscientists with thesauri creation for closely related, highly detailed neuroanatomical domains.

Abstract: Generating informational thesauri that classify, cross-reference, and retrieve diverse and highly detailed neuroscientific information requires identifying related neuroanatomical terms and acronyms within and between species (Gorin et al., 2001) Manual construction of such informational thesauri is laborious, and we describe implementing and evaluating a neuroanatomical term and acronym reconciliation (NTAR) system to assist domain experts with this task. NTAR is composed of two modules. The neuroanatomical term extraction (NTE) module employs a hidden Markov model (HMM) in conjunction with lexical rules to extract neuroanatomical terms (NT) and acronyms (NA) from textual material. The output of the NTE is formatted into collections of term- or acronym-indexed documents composed of sentences and word phrases extracted from textual material. The second information retrieval (IR) module utilizes a vector space model (VSM) and includes a novel, automated relevance feedback algorithm. The IR module retrieves statistically related neuroanatomical terms and acronyms in response to queried neuroanatomical terms and acronyms. Neuroanatomical terms and acronyms retrieval obtained from term-based inquiries were compared with (1) term retrieval obtained by including automated relevance feedback and with (2) term retrieval using “document-to-document” comparisons (context-based VSM). The retrieval of synonymous and similar primate and macaque thalamic terms and acronyms in response to a query list of human thalamic terminology by these three IR approaches was compared against a previously published, manually constructed concordance table of homologous cross-species terms and acronyms. Term-based VSM with automated relevance feedback retrieved 70% and 80% of these primate and macaque terms and acronyms, respectively, listed in the concordance table. Automated feedback algorithm correctly identified 87% of the macaque terms and acronyms that were independently selected by a domain expert as being appropriate for manual relevance feedback. Context-based VSM correctly retrieved 97% and 98% of the primate and macaque terms and acronyms listed in the term homology table. These results indicate that the NTAR system could assist neuroscientists with thesauri creation for closely related, highly detailed neuroanatomical domains.