Gil Rocha

Dr. Gil Rocha

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 January 2020 in Information
Verified
Journal Article
Open access
PDF file
ACAndré Ferreira Cruz
André Ferreira Cruz
GRGil Rocha
Gil Rocha
Henrique Lopes CardosoHenrique Lopes Cardoso
Henrique Lopes Cardoso
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.

29 March 2018 in Information
Verified
Journal Article
Open access
PDF file
GRGil Rocha
Gil Rocha
Henrique Lopes CardosoHenrique Lopes Cardoso
Henrique Lopes Cardoso
Recognizing textual entailment comprises the task of determining semantic entailment relations between text fragments. A text fragment entails another text fragment if, from the meaning of the former, one can infer the meaning of the latter. If such relation is bidirectional, then we are in the presence of a paraphrase. Automatically recognizing textual entailment relations captures major semantic inference needs in several natural language processing (NLP) applications. As in many NLP tasks, textual entailment corpora for English abound, while the same is not true for more resource-scarce languages such as Portuguese. Exploiting what seems to be the only Portuguese corpus for textual entailment and paraphrases (the ASSIN corpus), in this paper, we address the task of automatically recognizing textual entailment (RTE) and paraphrases from text written in the Portuguese language, by employing supervised machine learning techniques. We employ lexical, syntactic and semantic features, and analyze the impact of using semantic-based approaches in the performance of the system. We then try to take advantage of the bi-dialect nature of ASSIN to compensate its limited size. With the same aim, we explore modeling the task of recognizing textual entailment and paraphrases as a binary classification problem by considering the bidirectional nature of paraphrases as entailment relationships. Addressing the task as a multi-class classification problem, we achieve results in line with the winner of the ASSIN Challenge. In addition, we conclude that semantic-based approaches are promising in this task, and that combining data from European and Brazilian Portuguese is less straightforward than it may initially seem. The binary classification modeling of the problem does not seem to bring advantages to the original multi-class model, despite the outstanding results obtained by the binary classifier for recognizing textual entailments.

30 March 2020
Verified
Conference Paper
Open access
ACAndré Ferreira Cruz
André Ferreira Cruz
GRGil Rocha
Gil Rocha
Henrique Lopes CardosoHenrique Lopes Cardoso
Henrique Lopes Cardoso
Detecting bias in text is an increasingly relevant topic, given the information overload problem. Automating this task is crucial for our needs of quality news consumption. With this in mind, we explore modern deep learning approaches, including contextualized word embeddings and attention mechanisms, to compare the effects of different document representation choices. We design token-wise, sentence-wise and hierarchical document representations. Focusing on hyperpartisan news detection, we show that hierarchical attention mechanisms are able to better capture information at different levels of granularity (including intra and inter-sentence), which seems to be relevant for this task. With an accuracy of 82.5%, our best performing system is based on an ensemble of hierarchical attention networks with ELMo embeddings, achieving state-of-the-art performance on the SemEval-2019 Task4 dataset.

1 January 2019
Verified
Conference Paper
Open access
PDF file
ACAndré Ferreira Cruz
André Ferreira Cruz
GRGil Rocha
Gil Rocha
Henrique Lopes CardosoHenrique Lopes Cardoso
Henrique Lopes Cardoso
André Ferreira Cruz, Gil Rocha, Henrique Lopes Cardoso. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda. 2019.

1 January 2018
Verified
Conference Paper
Open access
GRGil Rocha
Gil Rocha
CSChristian Stab
Christian Stab
HCHenrique Lopes Cardoso
Henrique Lopes Cardoso
IGIryna Gurevych
Iryna Gurevych

1 January 2018
Verified
Conference Paper
Open access
ARAniketh Janardhan Reddy
Aniketh Janardhan Reddy
GRGil Rocha
Gil Rocha
DEDiego Esteves
Diego Esteves