André Ferreira Cruz’s research while affiliated with University of Porto and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (5)


On document representations for detection of biased news articles
  • Conference Paper

March 2020

·

66 Reads

·

8 Citations

André Ferreira Cruz

·

·


Figure 1. Coreference resolution examples. The third example was extracted from the Winograd Schema Challenge [2].
Figure 2. Typical architecture of a coreference resolution system.
Figure 3. Example of contradictions in the linking process [1]. Arrows represent positive coreference links.
Collection of general domain coreference resolution corpora.
Coreference Resolution: Toward End-to-End and Cross-Lingual Systems
  • Article
  • Full-text available

January 2020

·

592 Reads

·

14 Citations

Information

The task of coreference resolution has attracted considerable attention in the literature due to its importance in deep language understanding and its potential as a subtask in a variety of complex natural language processing problems. In this study, we outlined the field’s terminology, describe existing metrics, their differences and shortcomings, as well as the available corpora and external resources. We analyzed existing state-of-the-art models and approaches, and reviewed recent advances and trends in the field, namely end-to-end systems that jointly model different subtasks of coreference resolution, and cross-lingual systems that aim to overcome the challenges of less-resourced languages. Finally, we discussed the main challenges and open issues faced by coreference resolution systems.

Download



Citations (5)


... The HAN is a model capable of balancing the information in a current state, deciding whether updating it and how much the past information contributes to its new state. (Cruz et al, 2020;Moreno et al, 2019;M. Alzhrani, 2022;Gangula et al, 2019;Ko et al, 2023) Continued on next page Unidirectional LSTM retains information solely from preceding inputs as it has only processed data from the past. ...

Reference:

A systematic review of Hyperpartisan News detection: A Comprehensive Framework for Definition, Detection, and Evaluation
On document representations for detection of biased news articles
  • Citing Conference Paper
  • March 2020

... Resolving coreferent entities can be handled by detecting text spans that constitute entity mentions and grouping (clustering) these mentions into coreference chains based on the entities that they refer to. The task has been commonly formulated in one of three forms [2]: i) the mention-pair model where the goal is to determine whether two mentions are coreferent or not, ii) the mention-ranking model that aims to select the correct antecedent of a mention from a set of candidates, and iii) the entity-mention model with the goal of determining whether a mention is referring to an entity represented by a partially formed mention cluster or not. This challenging task plays a crucial role in text understanding and has been widely studied in various language processing applications, such as machine translation [3], question answering [4], and information extraction [5]. ...

Coreference Resolution: Toward End-to-End and Cross-Lingual Systems

Information

... Some of these illegal online actions target election contexts deliberately because they provide the best opportunities to have the most impact on political trends [5]. Propaganda modifies information so as to actively sway people's opinions and further a planned objective [6]. Broadly speaking, propaganda is the "dissemination of information facts, arguments, rumours, halftruths, or lies to affect public opinion. ...

On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings
  • Citing Conference Paper
  • January 2019

... We use a small set of linguistically-inspired style and complexity features, already proven to have good performance on a similar bias-detection task -hyperpartisan news detection (Cruz et al., 2019). Some of the features portray the article in which each sentence is incorporated, while others portray the sentence itself. ...

Team Fernando-Pessa at
  • Citing Conference Paper
  • January 2019

... The results reported here were partially supported by PORTULAN CLA-RIN-Research Infrastructure for the Science and Technology of Language, funded by Lisboa2020, Alentejo2020 and FCT-Fundação para a Ciência e Tecnologia under the Grant PINFRA/22117/2016. The PORTULAN CLARIN Workbench comprises a number of tools that are based on a large body of research work contributed by different authors and teams, which continues to grow and is acknowledged here: (Barreto et al., 2006;Branco et al., 2010Branco et al., , 2011Branco et al., , 2012Branco et al., , 2014Cruz et al., 2018;Veiga et al., 2011;Branco & Henriques, 2003;Silva et al., 2009;Rodrigues et al., 2016Rodrigues et al., , 2020Costa & Branco, 2012;Santos et al., 2019;Miranda et al., 2011). ...

Exploring Spanish Corpora for Portuguese Coreference Resolution