1,721,396 research outputs found
Educação: conhecimento, formação humana e consciência política – entrevista com Giovanni Semeraro
No full text Entrevista com o professor Giovanni Semeraro. Qual o papel da Educação na formação de cidadãos conscientes do mundo e dirigentes do próprio país? Onde entram, respectivamente, as escolas de ensino básico e as universidades, nesta missão? Estudantes e mestres estão inseridos neste processo? Você, leitor, já se perguntou e posicionou sobre essas questões? Há quem concorde que pontos como estes não merecem reflexão, já que não fazem parte da agenda pública de discussões da sociedade. Outros, no entanto, apontam não haver fórmulas mágicas para equacionar tais apontamentos, na medida em que, mesmo em pleno século XXI, consenso parece estar distante.A reflexão é necessária, aponta o Professor Giovanni Semeraro, Professor Titular de Filosofia da Educação na Universidade Federal Fluminense, Doutor em Educação pela Universidade Federal do Rio de Janeiro (UFRJ), com pós-doutorado na Itália. O ponto de partida é compreender que o debate e a conscientização da realidade na qual vivemos devem se fazer presentes dentro das próprias instituições de ensino. E que estas, além da formação intelectual, devem educar ao diálogo, ao respeito das diferenças e à democracia
Entrevista com o Profº Dr Giovanni Semeraro: Atualidade de Marx, organização popular e formação
Full text linkEntrevista concedida por e-mails enviados entre os dias 14 de Julho de 2021 e 17 de Agosto de 2021 a convite do Grupo de Estudos Marxistas: Marx e Gramsci da Universidade Federal de Uberlândia em reconhecimento por seu trabalho acadêmico e na International Gramsci Society - Brasil. Em nome da Revista Primordium, Fernando Tadeu Mondi Galine e o Grupo de Estudos Marxistas: Marx e Gramsci, prepararam e enviaram a entrevista. O Grupo de Estudos Marxistas: Marx e Gramsci da Universidade Federal de Uberlândia e a Revista Primordium agradecem ao Profº Dr Giovanni Semeraro por sua generosa participação
Comparing Word Sense Disambiguation and Distributional Models for Cross-Language Information Filtering
No full textIn this paper we deal with the problem of providing users
with cross-language recommendations by comparing two dierent content-
based techniques: the rst one relies on a knowledge-based word sense
disambiguation algorithm that uses MultiWordNet as sense inventory,
while the latter is based on the so-called distributional hypothesis and
exploits a dimensionality reduction technique called Random Indexing
in order to build language-independent user proles.
This paper summarizes the results already presented within the confer-
ence AI*IA 2011 [1]
Distributional models vs. Linked Data: exploiting crowdsourcing to personalize music playlists
No full textThis paper presents Play.me, a system that exploits socialmedia to generate personalized music playlists. First, we extracted userpreferences in music by mining Facebook profiles. Next, given this prelim-inary playlist based on explicit preferences, we enriched it by adding newartists related to those the user already likes. In this work two differentenrichment techniques are compared: the first one relies on knowledgestored on DBpedia while the latter is based on the similarity calculationsbetween semantic descriptions of the artists. A prototype version of thetool was made available online in order to carry out a preliminary userstudy to evaluate the best enrichment strategy. This paper summarizesthe results presented in EC-Web 2012 [3]
Myusic: a Content-based Music Recommender System based on eVSM and Social Media
No full textThis paper presents Myusic, a platform that leverages socialmedia to produce content-based music recommendations. The design ofthe platform is based on the insight that user preferences in music canbe extracted by mining Facebook profiles, thus providing a novel and ef-fective way to sift in large music databases and overcome the cold-startproblem as well. The content-based recommendation model implementedin Myusic is eVSM [4], an enhanced version of the vector space modelbased on distributional models, Random Indexing and Quantum Nega-tion. The effectiveness of the platform is evaluated through a preliminaryuser study performed on a sample of 50 persons. The results showed that74% of users actually prefer recommendations computed by social media-based profiles with respect to those computed by a simple heuristic basedon the popularity of artists, and confirmed the usefulness of performinguser studies because of the different outcomes they can provide withrespect to offline experiments
TV-Show Retrieval and Classification
No full textRecommender systems are popular tools to aid users in find-ing interesting and relevant TV shows and other digital video assets,based on implicitly defined user preferences. In this context, a commonassumption is that user preferences can be specified by program types(such as documentary, sports), and that an asset can be labeled by oneor more program types, thus allowing an initial coarse preselection ofpotentially interesting assets. Furthermore each asset has a short tex-tual description, which allows us to investigate whether it is possible toautomatically label assets with program type labels. We compare theVector Space Model (vsm) with more recent approaches to text classifi-cation, such as Logistic Regression (lr) and Random Indexing (ri) on alarge collection of TV-show descriptions. The experimental results showthatlris the best approach, butrioutperformsvsmunder particularconditions
A Comparative Study of Models for Answer Sentence Selection
No full textAnswer Sentence Selection is one of the steps typically involved in Question Answering. Question Answering is considered a hard task for natural language processing systems, since full solutions would require both natural language understanding and inference abilities. In this paper, we explore how the state of the art in answer selection has improved recently, comparing two of the best proposed models for tackling the problem: the Cross-attentive Convolutional Network and the BERT model. The experiments are carried out on two datasets, WikiQA and SelQA, both created for and used in open-domain question answering challenges. We also report on cross domain experiments with the two datasets
Automated short answer grading: A simple solution for a difficult task
Full text linkThe task of short answer grading is aimed at assessing the outcome of an exam by automatically analysing students’ answers in natural language and deciding whether they should pass or fail the exam. In this paper, we tackle this task training an SVM classifier on real data taken from a University statistics exam, showing that simple concatenated sentence embeddings used as features yield results around 0.90 F1, and that adding more complex distance-based features lead only to a slight improvement. We also release the dataset, that to our knowledge is the first freely available dataset of this kind in Italian.
Leveraging Encyclopedic Knowledge for Transparent and Serendipitous User Profiles
No full textThe main contribution of this work is the comparison of different techniques for representing user preferences extracted by analyzing data gathered from social networks, with the aim of constructing more transparent (human-readable) and serendipitous user profiles. We compared two different user models representations: one based on keywords and one exploiting encyclopedic knowledge extracted from Wikipedia. A preliminary evaluation involving 51 Facebook and Twitter users has shown that the use of an encyclopedic-based representation better reflects user preferences, and helps to introduce new interesting topics
Towards comprehensive and efficient information extraction across languages
Full text linkThe exponential growth of textual data shared online has created an urgent need for methods that can effectively extract, structure, and interpret information from vast and varied texts. Information Extraction (IE), a key area within Natural Language Processing (NLP), addresses this need by transforming unstructured text into structured formats enabling automated text analytics and decision-making. However, existing IE systems face substantial challenges in scalability and generalization. These challenges include limited labeled data for low-resource languages, computational demands that restrict accessibility to only well-resourced institutions, and a predominant focus on popular entities. Additionally, most IE tasks are entity-centric tasks (e.g. Named Entity Recognition, Entity Disambiguation, and Relation Extraction), thus overlooking the broader contextual richness present in many texts.
This thesis aims at advancing the field of IE by tackling these critical issues through novel resources, methodologies, and theoretical approaches aimed at fostering a multilingual, scalable, and semantically-enriched IE framework. To bridge the multilingual gap, we leverage a combination of neural and knowledge-based approaches and create multilingual datasets for NER and Relation Extraction, ensuring that IE systems can operate effectively across diverse linguistic settings. On the computational front, we propose optimizations designed to reduce the resource requirements of IE models, especially in the context of Entity Disambiguation, enabling broader adoption of NLP technologies by reducing dependence on high-performance hardware and extensive labeled datasets.
Additionally, this work challenges traditional IE frameworks by expanding the focus beyond named entities to encompass abstract concepts, idiomatic expressions, and tail entities, which are essential for a more nuanced and comprehensive understanding of texts. Through these contributions, this research aims to establish a robust foundation for multilingual, resource-efficient IE systems that can meet the evolving demands of global text analytics across varied languages, domains, and cultural contexts. Finally, to further encourage the usage and development of multilingual IE systems, we publicly release all the artifacts -- datasets and models -- introduced in this thesis
- …
