Online discussions can either bridge differences through constructive dialogue or amplify divisions through destructive interactions. paper proposes a computational approach to analyze dialogical relation patterns in YouTube comments, offering a fine-grained framework for controversy detection, enabling also analysis of individual contributions. experiments demonstrate that shallow learning methods, when equipped with these theoretically-grounded features, consistently outperform more complex language models in characterizing discourse quality at both comment-pair and conversation-chain levels.studies confirm that divisive rhetorical techniques serve as strong predictors of destructive communication patterns. work advances understanding of how communicative choices shape online discourse, moving beyond engagement metrics toward nuanced examination of constructive versus destructive dialogue patterns.

Computational medicine research requires clinical data for training and testing purposes, so the development of datasets composed of real hospital data is of utmost importance in this field. Most such data collections are in the English language, were collected in anglophone countries, and do not reflect other clinical realities, which increases the importance of national datasets for projects that hope to positively impact public health. This paper presents a new Brazilian Clinical Dataset containing over 70,000 admissions from 10 hospitals in two Brazilian states, composed of a sum total of over 2.5 million free-text clinical notes alongside data pertaining to patient information, prescription information, and exam results. This data was collected, organized, deidentified, and is being distributed via credentialed access for the use of the research community. In the course of presenting the new dataset, this paper will explore the new dataset’s structure, population, and potential benefits of using this dataset in clinical AI tasks.

The present work uses the Bidirectional Encoder Representations from Transformers (BERT) to process a sentence and its entities and indicate whether two named entities present in a sentence are related or not, constituting a binary classification problem. It was developed for the Portuguese language, considering the financial domain and exploring deep linguistic representations to identify a relation between entities without using other lexical-semantic resources. The results of the experiments show an accuracy of 86% of the predictions.

This work focuses on Portuguese Named Entity Recognition (NER) in the Geology domain. The only domain-specific dataset in the Portuguese language annotated for NER is the GeoCorpus. Our approach relies on BiLSTM-CRF neural networks (a widely used type of network for this area of research) that use vector and tensor embedding representations. Three types of embedding models were used (Word Embeddings, Flair Embeddings, and Stacked Embeddings) under two versions (domain-specific and generalized). The domain specific Flair Embeddings model was originally trained with a generalized context in mind, but was then fine-tuned with domain-specific Oil and Gas corpora, as there simply was not enough domain corpora to properly train such a model. Each of these embeddings was evaluated separately, as well as stacked with another embedding. Finally, we achieved state-of-the-art results for this domain with one of our embeddings, and we performed an error analysis on the language model that achieved the best results. Furthermore, we investigated the effects of domain-specific versus generalized embeddings.

Language Models have long been a prolific area of study in the field of Natural Language Processing (NLP). One of the newer kinds of language models, and some of the most used, are Word Embeddings (WE). WE are vector space representations of a vocabulary learned by a non-supervised neural network based on the context in which words appear. WE have been widely used in downstream tasks in many areas of study in NLP. These areas usually use these vector models as a feature in the processing of textual data. This paper presents the evaluation of newly released WE models for the Portuguese langauage, trained with a corpus composed of 4.9 billion tokens. The first evaluation presented an intrinsic task in which WEs had to correctly build semantic and syntactic relations. The second evaluation presented an extrinsic task in which the WE models were used in two downstream tasks: Named Entity Recognition and Semantic Similarity between Sentences. Our results show that a diverse and comprehensive corpus can often outperform a larger, less textually diverse corpus, and that batch training may cause quality loss in WE models.

Linguistic Inquiry and Word Count (LIWC) is a rich dictionary that map words into several psychological categories such as Affective, Social, Cognitive, Perceptual and Biological processes. In this work, we have used LIWC psycholinguistic categories to train regression models and predict emotion intensity in tweets for the EmoInt-2017 task. Results show that LIWC features may boost emotion intensity prediction on the basis of a low dimension set.

This paper presents the adaptation of an Entity Centric Model for Portuguese coreference resolution, considering 10 named entity categories. The model was evaluated on named e using the HAREM Portuguese corpus and the results are 81.0% of precision and 58.3% of recall overall, the resulting system is freely available

The task of Relation Extraction from texts is one of the main challenges in the area of Information Extraction, considering the required linguistic knowledge and the sophistication of the language processing techniques employed. This task aims at identifying and classifying semantic relations that occur between entities recognized in a given text. In this paper, we evaluated a Conditional Random Fields classifier for the extraction of any relation descriptor occurring between named entities (Organisation, Person and Place categories), as well as pre-defined relation types between these entities in Portuguese texts.

This paper presents Summ-it++, an enriched version the Summ-it corpus. In this new version, the corpus has received new semantic layers, named entity categories and relations between named entities, adding to the previous coreference annotation. In addition, we change the original Summ-it format to SemEval

This paper proposes a method to build bilingual dictionaries for specific domains defined by a parallel corpora. The proposed method is based on an original method that is not domain specific. Both the original and the proposed methods are constructed with previously available natural language processing tools. Therefore, this paper contribution resides in the choice and parametrization of the chosen tools. To illustrate the proposed method benefits we conduct an experiment over technical manuals in English and Portuguese. The results of our proposed method were analyzed by human specialists and our results indicates significant increases in precision for unigrams and muli-grams. Numerically, the precision increase is as big as 15% according to our evaluation.

This paper describes an experiment to compare four tools to recognize named entities in Portuguese texts. The experiment was made over the HAREM corpora, a golden standard for named entities recognition in Portuguese. The tools experimented are based on natural language processing techniques and also machine learning. Specifically, one of the tools is based on Conditional random fields, an unsupervised machine learning model that has being used to named entities recognition in several languages, while the other tools follow more traditional natural language approaches. The comparison results indicate advantages for different tools according to the different classes of named entities. Despite of such balance among tools, we conclude pointing out foreseeable advantages to the machine learning based tool.

Ontology alignment is a key process for enabling interoperability between ontology-based systems in the Linked Open Data age. From two input ontologies, this process generates an alignment (set of correspondences) between them. In this paper we present VOAR, a new web-based environment for ontology alignment visualization and manipulation. Within this graphical environment, users can manually create/edit correspondences and apply a set of operations on alignments (filtering, merge, difference, etc.). VOAR allows invoking external ontology matching systems that implement a specific alignment interface, so that the generated alignments can be manipulated within the environment. Evaluating multiple alignments together against a reference one can also be carried out, using classical evaluation metrics (precision, recall and f-measure). The status of each correspondence with respect to its presence or absence in reference alignment is visually represented. Overall, the main new aspect of VOAR is the visualization and manipulation of alignments at schema level, in an integrated, visual and web-based environment.

This paper presents a novel approach to deal with dictionary retrieval. This new approach is based on a very efficient and scalable theoretical structure called Multi-Terminal Multi-valued Decision Diagrams (MTMDD). Such tool allows the definition of very large, even multilingual, dictionaries without significant increase in memory demands, and also with virtually no additional processing cost. Besides the general idea of the novel approach, this paper presents a description of the technologies involved, and their implementation in a software package called WAGGER. Finally, we also present some examples of usage and possible applications of this dictionary retriever.

This paper presents a model to enrich an ontology with a thesaurus based on a domain corpus and WordNet. The model is applied to the data privacy domain and the initial domain resources comprise a data privacy ontology, a corpus of privacy laws, regulations and guidelines for projects. Based on these resources, a thesaurus is automatically generated. The thesaurus seeds are composed by the ontology concepts. For these seeds similar terms are extracted from the corpus using known thesaurus generation methods. A filtering process searches for semantic relations between seeds and similar terms within WordNet. As a result, these semantic relations are used to expand the ontology with relations between them and related terms in the corpus. The resulting resource is a hierarchical structure that can help on the ontology investigation and maintenance. The results allow the investigation of the domain knowledge with the support of semantic relations not present on the original ontology.

Ontology matching consists of generating a set of correspondences between the entities of two ontologies. This process is seen as a solution to data heterogeneity in ontology-based applications, enabling the interoperability between them. However, existing matching systems are designed by assuming that the entities of both source and target ontologies are written in the same languages ( English, for instance). Multi-lingual ontology matching is an open research issue. This paper describes an API for multi-lingual matching that implements two strategies, direct translation-based and indirect. The first strategy considers direct matching between two ontologies (i.e., without intermediary ontologies), with the help of external resources, i.e., translations. The indirect alignment strategy, proposed by (Jung et al., 2009), is based on composition of alignments. We evaluate these strategies using simple string similarity based matchers and three ontologies written in English, French, and Portuguese, an extension of the OAEI benchmark test 206.

In the field of ontology mapping, multilingual ontology mapping is an issue that is not well explored. This paper proposes a framework for mapping of multilingual Description Logics (DL) ontologies. First, the DL source ontology is translated to the target ontology language, using a lexical database or a dictionary, generating a DL translated ontology. The target and the translated ontologies are then used as input for the mapping process. The mappings are computed by specialized agents using different mapping approaches. Next, these agents use argumentation to exchange their local results, in order to agree on the obtained mappings. Based on their preferences and confidence of the arguments, the agents compute their preferred mapping sets. The arguments in such preferred sets are viewed as the set of globally acceptable arguments. A DL mapping ontology is generated as result of the mapping process. In this paper we focus on the process of generating the DL translated ontology.