Constructing a biodiversity terminological inventory

Abstract

The increasing growth of literature in biodiversity presents challenges to users who need to discover pertinent information in an efficient and timely manner. In response, text mining techniques offer solutions by facilitating the automated discovery of knowledge from large textual data. An important step in text mining is the recognition of concepts via their linguistic realisation, i.e., terms. However, a given concept may be referred to in text using various synonyms or term variants, making search systems likely to overlook documents mentioning less known variants, which are albeit relevant to a query term. Domain-specific terminological resources, which include term variants, synonyms and related terms, are thus important in supporting semantic search over large textual archives. This article describes the use of text mining methods for the automatic construction of a large-scale biodiversity term inventory. The inventory consists of names of species, amongst which naming variations are prevalent. We apply a number of distributional semantic techniques on all of the titles in the Biodiversity Heritage Library, to compute semantic similarity between species names and support the automated construction of the resource. With the construction of our biodiversity term inventory, we demonstrate that distributional semantic models are able to identify semantically similar names that are not yet recorded in existing taxonomies. Such methods can thus be used to update existing taxonomies semi-automatically by deriving semantically related taxonomic names from a text corpus and allowing expert curators to validate them. We also evaluate our inventory as a means to improve search by facilitating automatic query expansion. Specifically, we developed a visual search interface that suggests semantically related species names, which are available in our inventory but not always in other repositories, to incorporate into the search query. An assessment of the interface by domain experts reveals that our query expansion based on related names is useful for increasing the number of relevant documents retrieved. Its exploitation can benefit both users and developers of search engines and text mining applications.

Fig 1. Framework for constructing our biodiversity terminological inventory.

Fig 2. Top-N accuracy obtained by DSMs for bird names.

Fig 3. Precision@N versus recall@N obtained by DSMs for bird names when N is varied from 1 to 20.

Fig 4. Top-N accuracy of DSMs for mammal names.

Fig 5. Precision@N versus recall@N obtained by DSMs for mammal names when N is varied from 1 to 20.

Fig 6. Top-N accuracy obtained by DSMs for plant names.

Fig 7. Precision@N versus recall@N obtained by DSMs for plant names when N is varied from 1 to 20.

Fig 8. Visual search interface incorporating suggested semantically related names for query expansion.

A- Initial and expanded query. B- Search result list and context viewer. The context viewer on the left-hand side shows a zoomed out view of the retrieved list. Documents retrieved according to the expanded query are shown with a light blue background. C- Thumbnails with suggested names for query expansion. Apart from a relevant image, each thumbnail depicts the suggested term’s frequency within BHL documents, its relatedness to the query term, and the provenance of the suggestion, i.e., our term inventory or other external resources such as CoL, EoL and GBIF.

Fig 9. Ratings for the visual search interface given by thirteen users.

The red line indicates the median rating for each question.