Extraction and generalisation of variables from scientific publications

Abstract

Scientific theories and models in Earth science typically involve changing variables and their complex interactions, including correlations, causal relations and chains of positive/negative feedback loops. Variables tend to be complex rather than atomic entities and expressed as noun phrases containing multiple modifiers, e.g. oxygen depletion in the upper 500 m of the ocean or timing and magnitude of surface temperature evolution in the Southern Hemisphere in deglacial proxy records. Text mining from Earth science literature is therefore significantly different from biomedical text mining and requires different approaches and methods. Our approach aims at automatically locating and extracting variables and their direction of variation: increasing, decreasing or just changing. Variables are initially extracted by matching tree patterns onto the syntax trees of the source texts. Next, variables are generalised in order to enhance their similarity, facilitating hierarchical search and inference. This generalisation is accomplished by progressive pruning of syntax trees using a set of tree transformation operations. Text mining results are presented as a browsable variable hierarchy which allows users to inspect all mentions of a particular variable type in the text as well as any generalisations or specialisations. The approach is demonstrated on a corpus of 10k abstracts of Nature publications in the field of Marine science. We discuss experiences with this early prototype and outline a number of possible improvements and directions for future research.

Emerging approaches in literature-based discovery: techniques and performance review

“…In addition to methods such as the HBIN model (Sebastian et al. , 2017), a work such as an automatic extraction of variable terms from non-biomedical literatures (Marsi &Öztürk, 2015) is a good example of the initial steps toward this direction.…”

“…DARPA's Big Mechanism initiative (Cohen, 2015) encourages a greater usage of LBD systems for uncovering complex scientific mechanisms from diverse literatures. In addition to methods such as the HBIN model (Sebastian et al, 2017), a work such as an automatic extraction of variable terms from non-biomedical literatures (Marsi &Öztürk, 2015) is a good example of the initial steps toward this direction.…”

The NTNU System at SemEval-2017 Task 10: Extracting Keyphrases and Relations from Scientific Publications Using Multiple Conditional Random Fields

“…Maximal sequences and page ranking have been combined to discover latent keyphrases within scientific articles (Ortiz et al, 2010). Noun phrases containing multiple modifiers have been extracted from earth science publications and generalized by matching tree patterns to the syntax trees of the sources texts (Marsi and Öztürk, 2015). Keyphrase boundary classification has been regarded as a multi-task learning problem using deep recurrent neural network (Augenstein and Søgaard, 2017).…”

Event Causality Extraction from Natural Science Literature

“…The major challenges we face are the lack of resources like task specific annotated corpora, indexed literature databases covering the entire field, domain dependent NLP tools with good accuracies and knowledge resources (ontologies) as our target domain is almost unexplored. The resources and tools developed in biomedicine domain are not directly usable due to domain difference as shown in [24,25]. Therefore, to meet this goal, a constant effort is being employed to develop resources and tools.…”

“…In [25], authors describe an annotation scheme to annotate quantitative variables, their change events, correlations and causal relations among change events, and feedback loops from the abstracts and full-text journal papers collected from the nature publication. In [24], authors automatically identify and extract variables and their direction of changes using a tree pattern matching technique and generalise these variables by progressive pruning of syntax tree using tree transformation operations.…”