Search Results for author: Thiago Pardo

Found 25 papers, 1 papers with code

Semantically Inspired AMR Alignment for the Portuguese Language

no code implementations EMNLP 2020 Rafael Anchi{\^e}ta, Thiago Pardo

Abstract Meaning Representation (AMR) is a graph-based semantic formalism where the nodes are concepts and edges are relations among them.

AMR Parsing Sentence

PortiLexicon-UD: a Portuguese Lexical Resource according to Universal Dependencies Model

no code implementations LREC 2022 Lucelene Lopes, Magali Duran, Paulo Fernandes, Thiago Pardo

This paper presents PortiLexicon-UD, a large and freely available lexicon for Portuguese delivering morphosyntactic information according to the Universal Dependencies model.


Semantic-Based Opinion Summarization

1 code implementation RANLP 2021 Marcio Inácio, Thiago Pardo

The results show that a Machine Learning-based method produced summaries of higher quality, outperforming other literature techniques on manually constructed semantic graphs.

Opinion Summarization Sentiment Analysis

Toward Discourse-Aware Models for Multilingual Fake News Detection

no code implementations RANLP 2021 Francielle Vargas, Fabrício Benevenuto, Thiago Pardo

Statements that are intentionally misstated (or manipulated) are of considerable interest to researchers, government, security, and financial systems.

Deception Detection Fake News Detection

Evaluating Content Features and Classification Methods for Helpfulness Prediction of Online Reviews: Establishing a Benchmark for Portuguese

no code implementations WASSA (ACL) 2022 Rogério Sousa, Thiago Pardo

Over the years, the review helpfulness prediction task has been the subject of several works, but remains being a challenging issue in Natural Language Processing, as results vary a lot depending on the domain, on the adopted features and on the chosen classification strategy.


NILC at SR’20: Exploring Pre-Trained Models in Surface Realisation

no code implementations MSR (COLING) 2020 Marco Antonio Sobrevilla Cabezudo, Thiago Pardo

This paper describes the submission by the NILC Computational Linguistics research group of the University of S ̃ao Paulo/Brazil to the English Track 2 (closed sub-track) at the Surface Realisation Shared Task 2020.

Data-to-Text Generation

Back-Translation as Strategy to Tackle the Lack of Corpus in Natural Language Generation from Semantic Representations

no code implementations WS 2019 Marco Antonio Sobrevilla Cabezudo, Simon Mille, Thiago Pardo

This paper presents an exploratory study that aims to evaluate the usefulness of back-translation in Natural Language Generation (NLG) from semantic representations for non-English languages.

Machine Translation Text Generation +1

Towards a General Abstract Meaning Representation Corpus for Brazilian Portuguese

no code implementations WS 2019 Marco Antonio Sobrevilla Cabezudo, Thiago Pardo

Abstract Meaning Representation (AMR) is a recent and prominent semantic representation with good acceptance and several applications in the Natural Language Processing area.

NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models

no code implementations WS 2018 Marco Antonio Sobrevilla Cabezudo, Thiago Pardo

Additionally, we apply a bottom-up approach to build the sentence and, using language-specific lexicons, we produce the proper word form of each lemma in the sentence.

Language Modelling LEMMA +2

Cannot find the paper you are looking for? You can Submit a new open access paper.