The analysis of the text content in emails, blogs, tweets, forums and other forms of textual communication constitutes what we call text analytics. Text analytics is applicable to most industries: it can help analyze millions of emails; you can analyze customers’ comments and questions in forums; you can perform sentiment analysis using text analytics by measuring positive or negative perceptions of a company, brand, or product. Text Analytics has also been called text mining, and is a subcategory of the Natural Language Processing (NLP) field, which is one of the founding branches of Artificial Intelligence, back in the 1950s, when an interest in understanding text originally developed. Currently Text Analytics is often considered as the next step in Big Data analysis. Text Analytics has a number of subdivisions: Information Extraction, Named Entity Recognition, Semantic Web annotated domain’s representation, and many more. Several techniques are currently used and some of them have gained a lot of attention, such as Machine Learning, to show a semisupervised enhancement of systems, but they also present a number of limitations which make them not always the only or the best choice. We conclude with current and near future applications of Text Analytics.
22 February 2021 in BMC Medical Informatics and Decision Making
Background: The large volume of medical literature makes it difficult for healthcare professionals to keep abreast of the latest studies that support Evidence-Based Medicine. Natural language processing enhances the access to relevant information, and gold standard corpora are required to improve systems. To contribute with a new dataset for this domain, we collected the Clinical Trials for Evidence-Based Medicine in Spanish (CT-EBM-SP) corpus.Methods: We annotated 1200 texts about clinical trials with entities from the Unified Medical Language System semantic groups: anatomy (ANAT), pharmacological and chemical substances (CHEM), pathologies (DISO), and lab tests, diagnostic or therapeutic procedures (PROC). We doubly annotated 10% of the corpus and measured inter-annotator agreement (IAA) using F-measure. As use case, we run medical entity recognition experiments with neural network models.Results: This resource contains 500 abstracts of journal articles about clinical trials and 700 announcements of trial protocols (292 173 tokens). We annotated 46 699 entities (13.98% are nested entities). Regarding IAA agreement, we obtained an average F-measure of 85.65% (±4.79, strict match) and 93.94% (±3.31, relaxed match). In the use case experiments, we achieved recognition results ranging from 80.28% (±00.99) to 86.74% (±00.19) of average F-measure.Conclusions: Our results show that this resource is adequate for experiments with state-of-the-art approaches to biomedical named entity recognition. It is freely distributed at:http://www.lllf.uam.es/ESP/nlpmedterm_en.html. The methods are generalizable to other languages with similar available sources.
This chapter shows the application of statistical tests to a corpus of spontaneous spoken Spanish. Our goal is to find representative differences between different parts of the corpus. To this end, we tagged n-grams in the corpus with features related to the speaker (age, gender, etc.), or the context (dialogue, monologue, media, etc.), and applied the log-likelihood test (Dunning, 1993) in order to find the most distinctive lexical or grammatical items for each specific socio-contextual feature. This chapter is divided in three sections. In the first, the characteristics of the spoken corpus are shown. The second section is devoted to the explanation of the computational tool. In the third section, a first rough estimate of the results obtained is given, as well as possible applications of the model.
1 March 2019 in International Journal of Interactive Multimedia and Artificial Intelligence
Artificial Intelligence (AI) and its branch Natural Language Processing (NLP) in particular are main contributors to recent advances in classifying documentation and extracting information from assorted fields, Medicine being one that has gathered a lot of attention due to the amount of information generated in public professional journals and other means of communication within the medical profession. The typical information extraction task from technical texts is performed via an automatic term recognition extractor. Automatic Term Recognition (ATR) from technical texts is applied for the identification of key concepts for information retrieval and, secondarily, for machine translation. Term recognition depends on the subject domain and the lexical patterns of a given language, in our case, Spanish, Arabic and Japanese. In this article, we present the methods and techniques for creating a biomedical corpus of validated terms, with several tools for optimal exploitation of the information therewith contained in said corpus. This paper also shows how these techniques and tools have been used in a prototype.
1 October 2013 in Procedia - Social and Behavioral Sciences
This article describes the MultiMedica corpus, a multilingual collection of Spanish, Japanese, and Arabic texts from the biomedical domain. This novel combination of languages has been chosen with two purposes: the contrastive study of three languages that are typologically and genetically different, and the creation of a gold standard to develop and evaluate an Automatic Term Recognition (ATR) system. A total of 51,476 documents have been collected from the Web, and the corpus contains over seven and a half million words. Most documents were written by medical doctors and edited by journalists for the general public. Each text has been tagged for Part-of-Speech and indexed in an Information Retrieval system and a concordance interface that is aimed at students of Translation, Medicine, and Medical Humanities
1 December 2018 in Revista Signos. Estudios de Lingüística
El origen de esta investigación está en la redacción de un diccionario de anglicismos del español de los Estados Unidos. Con el fin de incorporar anglicismos de reciente introducción en español, se procedió a la búsqueda de mensajes emitidos en la red social Twitter reuniendo un gran corpus de mensajes que, mediante la aplicación de filtros sucesivos, permitieron obtener una relación final de más de 500 candidatos de anglicismos que podrían ser incorporados al diccionario. Este estudio ofrece un análisis contextualizado de la relación de candidatos a anglicismos elaborada mediante la aplicación de un método de búsqueda en el corpus. El análisis permite tomar decisiones sobre qué anglicismos pueden incorporarse al diccionario y cuáles no, de acuerdo a los fines del repertorio lexicográfico. Asimismo, el análisis lingüístico de las formas seleccionadas finalmente para su incorporación al diccionario revela el perfil de los anglicismos que se están introduciendo en el español estadounidense, en su dimensión ortográfica, gramatical y léxico-semántica.