BioNorm: deep learning-based event normalization for the curation of reaction databases

Motivation A biochemical reaction, bio-event, depicts the relationships between participating entities. Current text mining research has been focusing on identifying bio-events from scientific literature. However, rare efforts have been dedicated to normalize bio-events extracted from scientific literature with the entries in the curated reaction databases, which could disambiguate the events and further support interconnecting events into biologically meaningful and complete networks. Results In this paper, we propose BioNorm, a novel method of normalizing bio-events extracted from scientific literature to entries in the bio-molecular reaction database, e.g. IntAct. BioNorm considers event normalization as a paraphrase identification problem. It represents an entry as a natural language statement by combining multiple types of information contained in it. Then, it predicts the semantic similarity between the natural language statement and the statements mentioning events in scientific literature using a long short-term memory recurrent neural network (LSTM). An event will be normalized to the entry if the two statements are paraphrase. To the best of our knowledge, this is the first attempt of event normalization in the biomedical text mining. The experiments have been conducted using the molecular interaction data from IntAct. The results demonstrate that the method could achieve F-score of 0.87 in normalizing event-containing statements. Availability and implementation The source code is available at the gitlab repository https://gitlab.com/BioAI/leen and BioASQvec Plus is available on figshare https://figshare.com/s/45896c31d10c3f6d857a.

Cognitive Models Underlying Students' Formulation of Simple Linear Equations

Data are presented to show that errors in formulating algebraic equations are not primarily due to syntactic translation, as has been assumed in the literature. Furthermore, it is shown that the reversal error is common even when none of the previously published causes of the error is applicable. A new explanation is required and is proposed in this paper. An examination of students' errors leads us to suggest that students generally construct from the natural language statement a cognitive model of compared unequal quantities. They formulate equations by trying to represent the model directly or by drawing information from it. This hypothesis is supported by research on the comprehension of relationships by linguists, pyscholinguists and psychologists. Data were collected from 281 students in grade 9 in free response format and from 1048 students in grades 8, 9, and 10 who completed a multiple-choice item.