Spatial information in text enables to understand the geographical context and relationships within text for better decision-making across various domains such as disease surveillance, disaster management and other location based services. Therefore, it is crucial to understand the precise geographical context for location-sensitive applications. In response to this necessity, we introduce the GeospaCy software tool, designed for the extraction and georeferencing of spatial information present in textual data. GeospaCy fulfils two primary objectives: 1) Geoparsing, which involves extracting spatial expressions, encompassing place names and associated spatial relations within the text data, and 2) Geocoding, which facilitates the assignment of geographical coordinates to the spatial expressions extracted during the Geoparsing task. Geoparsing is evaluated with a disease news article dataset consisting of event information, whereas a qualitative evaluation of geographical coordinates (polygons/geometries) of spatial expressions is performed by end-users for Geocoding task.

We present EpidBioBERT, a biosurveillance epidemiological document tagger for disease surveillance over PADI-Web system. Our model is trained on PADI-Web corpus which contains news articles on Animal Diseases Outbreak extracted from the web. We train a classifier to discriminate between relevant and irrelevant documents based on their epidemiological thematic feature content in preparation for further epidemiology information extraction. Our approach proposes a new way to perform epidemiological document classification by enriching epidemiological thematic features namely disease, host, location and date, which are used as inputs to our epidemiological document classifier. We adopt a pre-trained biomedical language model with a novel fine tuning approach that enriches these epidemiological thematic features. We find these thematic features rich enough to improve epidemiological document classification over a smaller data set than initially used in PADI-Web classifier. This improves the classifiers ability to avoid false positive alerts on disease surveillance systems. To further understand information encoded in EpidBioBERT, we experiment the impact of each epidemiology thematic feature on the classifier under ablation studies. We compare our biomedical pre-trained approach with a general language model based model finding that thematic feature embeddings pre-trained on general English documents are not rich enough for epidemiology classification task. Our model achieves an F1-score of 95.5% over an unseen test set, with an improvement of +5.5 points on F1-Score on the PADI-Web classifier with nearly half the training data set.

Animal diseases-related news articles are richin information useful for risk assessment. In this paper, we explore a method to automatically retrieve sentence-level epidemiological information. Our method is an incremental approach to create and expand patterns at both lexical and syntactic levels. Expert knowledge input are used at different steps of the approach. Distributed vector representations (word embedding) were used to expand the patterns at the lexical level, thus alleviating manual curation. We showed that expert validation was crucial to improve the precision of automatically generated patterns.

The Platform for Automated extraction of animal Disease Information from the web (PADI-web) is an automated system which monitors the web for monitoring and detecting emerging animal infectious diseases. The tool automatically collects news via customised multilingual queries, classifies them and extracts epidemiological information. We detail the processing of multilingual online sources by PADI-web and analyse the translated outputs in a case study

Dans le contexte des masses de données aujourd’hui disponibles, de nombreux travaux liés à l’analyse de l’information spatiale s’appuient sur l’exploitation des données textuelles. La communication médiée (SMS, tweets, etc.) véhiculant des informations spatiales prend une place prépondérante. L’objectif du travail présenté dans cet article consiste à extraire ces informations spatiales à partir d’un corpus authentique de SMS en français. Nous proposons un processus dans lequel, dans un premier temps, nous extrayons de nouvelles entités spatiales (par exemple, motpellier, montpeul à associer au toponyme Montpellier). Dans un second temps, nous identifions de nouvelles relations spatiales qui précèdent les entités spatiales (par exemple, sur, par, pres, etc.). La tâche est difficile et complexe en raison de la spécificité du langage SMS qui repose sur une écriture peu standardisée (apparition de nombreux lexiques, utilisation massive d’abréviations, variation par rapport à l’écrit classique, etc.). Les expérimentations qui ont été réalisées à partir du corpus 88milSMS mettent en relief la robustesse de notre système pour identifier de nouvelles entités et relations spatiales.

With the explosive growth of online social media (forums, blogs, and social networks), exploitation of these new information sources has become essential. Our work is based on the sud4science project. The goal of this project is to perform multidisciplinary work on a corpus of authentic SMS, in French, collected in 2011 and anonymised (88milSMS corpus: http://88milsms.huma-num.fr). This paper highlights a new method to integrate opinion detection knowledge from an SMS corpus by combining lexical and semantic information. More precisely, our approach gives more weight to words with a sentiment (i.e. presence of words in a dedicated dictionary) for a classification task based on three classes: positive, negative, and neutral. The experiments were conducted on two corpora: an elongated SMS corpus (i.e. repetitions of characters in messages) and a non-elongated SMS corpus. We noted that non-elongated SMS were much better classified than elongated SMS. Overall, this study highlighted that the integration of semantic knowledge always improves classification.

Polysemy is the capacity for a word to have multiple meanings. Polysemy detection is a first step for Word Sense Induction (WSI), which allows to find different meanings for a term. The polysemy detection is also important for information extraction (IE) systems. In addition, the polysemy detection is important for building/enriching terminologies and ontologies. In this paper, we present a novel approach to detect if a biomedical term is polysemic, with the long term goal of enriching biomedical ontologies. This approach is based on the extraction of new features. In this context we propose to extract features following two manners: (i) extracted directly from the text dataset, and (ii) from an induced graph. Our method obtains an Accuracy and F-Measure of 0.978.

Timeliness and precision for detection of infectious animal disease outbreaks from the information published on the web is crucial for prevention against their spread. We propose a generic method to enrich and extend the use of different expressions as queries in order to improve the acquisition of relevant disease related pages on the web. Our method combines a text mining approach to extract terms from corpora of relevant disease outbreak documents, and domain expert elicitation (Delphi method) to propose expressions and to select relevant combinations between terms obtained with text mining. In this paper we evaluated the performance as queries of a number of expressions obtained with text mining and validated by a domain expert and expressions proposed by a panel of 21 domain experts. We used African swine fever as an infectious animal disease model. The expressions obtained with text mining outperformed as queries the expressions proposed by domain experts. However, domain experts proposed expressions not extracted automatically. Our method is simple to conduct and flexible to adapt to any other animal infectious disease and even in the public health domain.

Le travail présenté dans cet article se situe dans le cadre de l’identification de termes spécialisés (unités de mesure) à partir de données textuelles pour enrichir une Ressource Termino-Ontologique (RTO). La première étape de notre méthode consiste à prédire la localisation des variants d’unités de mesure dans les documents. Nous avons utilisé une méthode reposant sur l’apprentissage supervisé. Cette méthode permet de réduire sensiblement l’espace de recherche des variants tout en restant dans un contexte optimal de recherche (réduction de 86% de l’espace de recherché sur le corpus étudié). La deuxième étape du processus, une fois l’espace de recherche réduit aux variants d’unités, utilise une nouvelle mesure de similarité permettant d’identifier automatiquement les variants découverts par rapport à un terme d’unité déjà référencé dans la RTO avec un taux de précision de 82% pour un seuil au dessus de 0.6 sur le corpus étudié.

In this paper, we propose a method for aligning text messages (entitled AlignSMS) in order to automatically build an SMS dictionary. An extract of 100 text messages from the 88milSMS corpus (Panckhurst el al., 2013, 2014) was used as an initial test. More than 90,000 authentic text messages in French were collected from the general public by a group of academics in the south of France in the context of the sud4science project (http://www.sud4science.org). This project is itself part of a vast international SMS data collection project, entitled sms4science (http://www.sms4science.org, Fairon et al. 2006, Cougnon, 2014). After corpus collation, pre-processing and anonymisation (Accorsi et al., 2012, Patel et al., 2013), we discuss how “raw” anonymised text messages can be transcoded into normalised text messages, using a statistical alignment method. The future objective is to set up a hybrid (symbolic/statistic) approach based on both grammar rules and our statistical AlignSMS method.

Le titrage automatique de documents textuels est une tâche essentielle pour plusieurs applications (titrage de mails, génération automatique de sommaires, synthèse de documents, etc.). Cette étude présente une méthode de construction de titres courts appliquée à un corpus d’articles journalistiques via des méthodes de Fouille du Web. Il s’agit d’une première étape cruciale dans le but de proposer une méthode de construction de titres plus complexes. Dans cet article, nous présentons une méthode proposant des titres tenant compte de leur cohérence par rapport au texte, par rapport au Web, ainsi que de leur contexte dynamique. L’évaluation de notre approche indique que nos titres construits automatiquement sont informatifs et/ou accrocheurs.

Le marché d’offres d’emploi et des candidatures sur Internet connaît une croissance exponentielle. Ceci implique des volumes d’information (majoritairement sous la forme de texte libre) qu’il n’est plus possible de traiter manuellement. Une analyse et catégorisation assistées nous semble pertinente en réponse à cette problématique. Nous proposons E-Gen, système qui a pour but l’analyse et catégorisation assistés d’offres d’emploi et des réponses des candidats. Dans cet article nous présentons plusieurs stratégies, reposant sur les modèles vectoriel et probabiliste, afin de résoudre la problématique du profilage des candidatures en fonction d’une offre précise. Nous avons évalué une palette de mesures de similarité afin d’effectuer un classement pertinent des candidatures au moyen des courbes ROC. L’utilisation d’une forme de relevance feedback a permis de surpasser nos résultats sur ce problème difficile et sujet à une grande subjectivité.