The Content Types Dataset: a New Resource to Explore Semantic and
            Functional Characteristics of Texts

Sprugnoli, Rachele; Caselli, Tommaso; Tonelli, Sara; Moretti, Giovanni

doi:10.18653/v1/e17-2042

Cited by 6 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More recently, Yu et al (2016) used a hybrid deep neural network combined with a Hidden Markov Model (DNN-HMM) to segment speech transcripts from broadcast news to a sequence of stories. Similar to our approach, (Sprugnoli et al, 2017) used CRFs and SVMs for the classification of automatic classification of Content Types, a novel task that was introduced to provide cues to access the structure of a document's types of functional content.…”

Section: Related Workmentioning

confidence: 99%

Improving the Identification of the Discourse Function of News Article Paragraphs

Banisakher¹,

Yarlott²,

Aldawsari³

et al. 2020

Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events

View full text Add to dashboard Cite

Identifying the discourse structure of documents is an important task in understanding written text. Building on prior work, we demonstrate an improved approach to automatically identifying the discourse function of paragraphs in news articles. We start with the hierarchical theory of news discourse developed by van Dijk (1988) which proposes how paragraphs function within news articles. This discourse information is a level intermediate between phrase-or sentence-sized discourse segments and document genre, characterizing how individual paragraphs convey information about the events in the storyline of the article. Specifically, the theory categorizes the relationships between narrated events and (1) the overall storyline (such as MAIN EVENTS, BACKGROUND, or CONSEQUENCES) as well as ( 2) commentary (such as VERBAL REAC-TIONS and EVALUATIONS). We trained and tested a linear chain conditional random field (CRF) with new features to model van Dijk's labels and compared it against several machine learning models presented in previous work. Our model significantly outperformed all baselines and prior approaches, achieving an average of 0.71 F 1 score which represents a 31.5% improvement over the previously bestperforming support vector machine model.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving the Identification of the Discourse Function of News Article Paragraphs

Banisakher¹,

Yarlott²,

Aldawsari³

et al. 2020

Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events

View full text Add to dashboard Cite

show abstract

“…"Bieber fever" refers to avid supporters of Justin Bieber) and those discussing an infectious disease outbreak (43,51,52). Machine learning methods can also be used to distinguish between ambiguities in dates and locations, such as past and present outbreaks in articles that discuss historical context (53,54). Novel applications for ML methods are also being developed, such as structuring disease case information into epidemiological line lists (a listing of individuals affected by the disease and related information; i.e.…”

Section: Artificial Intelligence Applicationsmentioning

confidence: 99%

Risk assessment strategies for early detection and prediction of infectious disease outbreaks associated with climate change

Rees

Gachon

et al. 2019

CCDR

View full text Add to dashboard Cite

A new generation of surveillance strategies is being developed to help detect emerging infections and to identify the increased risks of infectious disease outbreaks that are expected to occur with climate change. These surveillance strategies include event-based surveillance (EBS) systems and risk modelling. The EBS systems use open-source internet data, such as media reports, official reports, and social media (such as Twitter) to detect evidence of an emerging threat, and can be used in conjunction with conventional surveillance systems to enhance early warning of public health threats. More recently, EBS systems include artificial intelligence applications such machine learning and natural language processing to increase the speed, capacity and accuracy of filtering, classifying and analysing health-related internet data. Risk modelling uses statistical and mathematical methods to assess the severity of disease emergence and spread given factors about the host (e.g. number of reported cases), pathogen (e.g. pathogenicity) and environment (e.g. climate suitability for reservoir populations). The types of data in these models are expanding to include health-related information from open-source internet data and information on mobility patterns of humans and goods. This information is helping to identify susceptible populations and predict the pathways from which infections might spread into new areas and new countries. As a powerful addition to traditional surveillance strategies that identify what has already happened, it is anticipated that EBS systems and risk modelling will increasingly be used to inform public health actions to prevent, detect and mitigate the climate change increases in infectious diseases. Affiliations

show abstract

“…la « fièvre Justin Bieber » fait référence aux fans du chanteur) et les articles portant sur l'éclosion d'une maladie infectieuse (43,51,52). L'apprentissage automatique peut également servir à éclaircir les ambiguïtés dans les dates et les lieux, comme les éclosions passées et les éclosions en cours, dans les articles discutant du contexte historique (53,54). De plus, on élabore des applications avant-gardistes de l'apprentissage automatique, telles que la structuration des données sur les cas sous forme de listes de parcours des éléments épidémiologiques (la liste des patients infectés et l'information connexe : état de santé, sexe, lieu, date d'apparition de la maladie, hospitalisation, etc.)…”

Section: Applications De L'intelligence Artificielleunclassified

Stratégie d’évaluation des risques servant à la détection précoce et à la prédiction des éclosions de maladies infectieuses associées aux changements climatiques

Rees¹,

Ng²,

Gachon³

et al. 2019

RMTC

View full text Add to dashboard Cite

The Content Types Dataset: a New Resource to Explore Semantic and Functional Characteristics of Texts

Cited by 6 publications

References 18 publications

Improving the Identification of the Discourse Function of News Article Paragraphs

Improving the Identification of the Discourse Function of News Article Paragraphs

Risk assessment strategies for early detection and prediction of infectious disease outbreaks associated with climate change

Stratégie d’évaluation des risques servant à la détection précoce et à la prédiction des éclosions de maladies infectieuses associées aux changements climatiques

Contact Info

Product

Resources

About