Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    André Fernandes Santos
  • Cargo

    Estudante Externo
  • Desde

    05 abril 2017
Publicações

2023

A Game with a Purpose for Building Crowdsourced Semantic Relations Datasets for Named Entities

Autores
dos Santos, AF; Leal, JP;

Publicação
Lecture Notes in Networks and Systems

Abstract
Semantic measures evaluate and compare the strength of relations between entities. To assess their accuracy, semantic measures are compared against human-generated gold standards. Existing semantic gold standards are mainly focused on concepts. Nevertheless, semantic measures are frequently applied both to concepts and instances. Games with a purpose are used to offload to humans computational or data collection needs, improving results by using entertainment as motivation for higher engagement. We present Grettir, a system which allows the creation of crowdsourced semantic relations datasets for named entities through a game with a purpose where participants are asked to compare pairs of entities. We describe the system architecture, the algorithms and implementation decisions, the first implemented instance – dedicated to the comparison of music artists – and the results obtained. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

2021

Derzis: A Path Aware Linked Data Crawler

Autores
dos Santos, AF; Leal, JP;

Publicação
10th Symposium on Languages, Applications and Technologies, SLATE 2021, July 1-2, 2021, Vila do Conde/Póvoa de Varzim, Portugal.

Abstract
Consuming Semantic Web data presents several challenges, from the number of datasets it is composed of, to the (very) large size of some of those datasets and the uncertain availability of querying endpoints. According to its core principles, accessing linked data can be done simply by dereferencing the IRIs of RDF resources. This is a light alternative both for clients and servers when compared to dataset dumps or SPARQL endpoints. The linked data interface does not support complex querying, but using it recursively may suffice to gather information about RDF resources, or to extract the relevant sub-graph which can then be processed and queried using other methods. We present Derzis1, an open source semantic web crawler capable of traversing the linked data cloud starting from a set of seed resources. Derzis maintains information about the paths followed while crawling, which allows to define property path-based restrictions to the crawling frontier.

2020

DAOLOT: A Semantic Browser

Autores
Silva, JB; Santos, A; Leal, JP;

Publicação
9th Symposium on Languages, Applications and Technologies, SLATE 2020, July 13-14, 2020, School of Technology, Polytechnic Institute of Cávado and Ave, Portugal (Virtual Conference).

Abstract
The goal of the Semantic Web is to allow the software agents around us and AIs to extract information from the Internet as easily as humans do. This semantic web is a network of connected graphs, where relations between concepts and entities make up a layout that is very easy for machines to navigate. At the moment, there are only a few tools that enable humans to navigate this new layer of the Internet, and those that exist are for the most part very specialized tools that require from the user a lot of pre-existing knowledge about the technologies behind this structure. In this article we report on the development of DAOLOT, a search engine that allows users with no previous knowledge of the semantic web to take full advantage of its information network. This paper presents its design, the algorithm behind it and the results of the validation testing conducted with users. The results of our validation testing show that DAOLOT is useful and intuitive to users, even those without any previous knowledge of the field, and provides curated information from multiple sources instantly about any topic.

2013

Applying a text mining framework to the extraction of numerical parameters from scientific literature in the biotechnology domain

Autores
Santos, A; Nogueira, R; Lourenço, A;

Publicação
ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal

Abstract
Scientific publications are the main vehicle to disseminate information in the field of biotechnology for wastewater treatment. Indeed, the new research paradigms and the application of high-throughput technologies have increased the rate of publication considerably. The problem is that manual curation becomes harder, prone-to-errors and time-consuming, leading to a probable loss of information and inefficient knowledge acquisition. As a result, research outputs are hardly reaching engineers, hampering the calibration of mathematical models used to optimize the stability and performance of biotechnological systems. In this context, we have developed a data curation workflow, based on text mining techniques, to extract numerical parameters from scientific literature, and applied it to the biotechnology domain. A workflow was built to process wastewater-related articles with the main goal of identifying physico-chemical parameters mentioned in the text. This work describes the implementation of the workflow, identifies achievements and current limitations in the overall process, and presents the results obtained for a corpus of 50 full-text documents.

2012

Structural alignment of plain text books

Autores
Santos, A; Almeida, JJ; Carvalho, N;

Publicação
LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION

Abstract
Text alignment is one of the main processes for obtaining parallel corpora. When aligning two versions of a book, results are often affected by unpaired sections - sections which only exist in one of the versions of the book. We developed Text : : Perfide : : BookSync, a Perl module which performs books synchronization (structural alignment based on section delimitation), provided they have been previously annotated by Text : : Perfide : : BookCleaner. We discuss the need for such a tool and several implementation decisions. The main functions are described, and examples of input and output are presented. Text : : Perfide : : PartialAlign is an extension of the partialAlign.py tool bundled with hunalign which proposes an alternative methods for splitting bitexts.