Search

Multi-label document classification is a traditional task in NLP. Compared to single-label classification, each document can be assigned multiple classes. This problem is crucially important in various domains, such as tagging scientific articles. Documents are often structured into several sections such as abstract and title. Current approaches treat different sections equally for multi-label classification. We argue that this is not a realistic assumption, leading to sub-optimal results. Instead, we propose a new method called Learning Section Weights (LSW), leveraging the contribution of each distinct section for multi-label classification. Via multiple feed-forward layers, LSW learns to assign weights to each section of, and incorporate the weights in the prediction. We demonstrate our approach on scientific articles. Experimental results on public (arXiv) and private (Elsevier) datasets confirm the superiority of LSW, compared to state-of-the-art multi-label document classification methods. In particular, LSW achieves a 1.3% improvement in terms of macro averaged F1-score while it achieves 1.3% in terms of macro averaged recall on the publicly available arXiv dataset., Comment: 7 pages, 4 figures, 5 tables

Healthcare professionals are generating a substantial volume of clinical data in narrative form. As healthcare providers are confronted with serious time constraints, they frequently use telegraphic phrases, domain-specific abbreviations and shorthand notes. Efficient clinical text processing tools need to cope with the recognition and resolution of abbreviations, a task that has been extensively studied for English documents. Despite the outstanding number of clinical documents written worldwide in Spanish, only a marginal amount of studies has been published on this subject. In clinical texts, as opposed to the medical literature, abbreviations are generally used without their definitions or expanded forms. The aim of the first Biomedical Abbreviation Recognition and Resolution (BARR) track, posed at the IberEval 2017 evaluation campaign, was to assess and promote the development of systems for generating a sense inventory of medical abbreviations. The BARR track required the detection of mentions of abbreviations or short forms and their corresponding long forms or definitions from Spanish medical abstracts. For this track, the organizers provided the BARR medical document collection, the BARR corpus of manually annotated abstracts labelled by domain experts and the BARR-Markyt evaluation platform. A total of 7 teams submitted 25 runs for the two BARR subtasks: (a) the identification of mentions of abbreviations and their definitions and (b) the correct detection of short form-long form pairs. Here we describe the BARR track setting, the obtained results and the methodologies used by participating systems. The BARR task summary, corpus, resources and evaluation tool for testing systems beyond this campaign are available at: http://temu.inab.org ., We acknowledge the Encomienda MINETAD-CNIO/OTG Sanidad Plan TL and Open-Minted (654021) H2020 project for funding., Postprint (published version)

Objective To create a multilingual gold-standard corpus for biomedical concept recognition. Materials and methods We selected text units from different parallel corpora (Medline abstract titles, drug labels, biomedical patent claims) in English, French, German, Spanish, and Dutch. Three annotators per language independently annotated the biomedical concepts, based on a subset of the Unified Medical Language System and covering a wide range of semantic groups. To reduce the annotation workload, automatically generated preannotations were provided. Individual annotations were automatically harmonized and then adjudicated, and cross-language consistency checks were carried out to arrive at the final annotations. Results The number of final annotations was 5530. Inter-annotator agreement scores indicate good agreement (median F-score 0.79), and are similar to those between individual annotators and the gold standard. The automatically generated harmonized annotation set for each language performed equally well as the best annotator for that language. Discussion The use of automatic preannotations, harmonized annotations, and parallel corpora helped to keep the manual annotation efforts manageable. The inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques. Conclusion To our knowledge, this is the first gold-standard corpus for biomedical concept recognition in languages other than English. Other distinguishing features are the wide variety of semantic groups that are being covered, and the diversity of text genres that were annotated

Objective To create a multilingual gold-standard corpus for biomedical concept recognition. Materials and methods We selected text units from different parallel corpora (Medline abstract titles, drug labels, biomedical patent claims) in English, French, German, Spanish, and Dutch. Three annotators per language independently annotated the biomedical concepts, based on a subset of the Unified Medical Language System and covering a wide range of semantic groups. To reduce the annotation workload, automatically generated preannotations were provided. Individual annotations were automatically harmonized and then adjudicated, and cross-language consistency checks were carried out to arrive at the final annotations. Results The number of final annotations was 5530. Inter-annotator agreement scores indicate good agreement (median F-score 0.79), and are similar to those between individual annotators and the gold standard. The automatically generated harmonized annotation set for each language performed equally well as the best annotator for that language. Discussion The use of automatic preannotations, harmonized annotations, and parallel corpora helped to keep the manual annotation efforts manageable. The inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques. Conclusion To our knowledge, this is the first gold-standard corpus for biomedical concept recognition in languages other than English. Other distinguishing features are the wide variety of semantic groups that are being covered, and the diversity of text genres that were annotated