NILC at WebNLG+: Pretrained Sequence-to-Sequence Models on RDF-to-Text Generation

no code implementations • ACL (WebNLG, INLG) 2020 • Marco Antonio Sobrevilla Cabezudo, Thiago A. S. Pardo

This paper describes the submission by the NILC Computational Linguistics research group of the University of São Paulo/Brazil to the RDF-to-Text task for English at the WebNLG+ challenge.

Data-to-Text Generation

Predicting Sentence-Level Factuality of News and Bias of Media Outlets

no code implementations • 27 Jan 2023 • Francielle Vargas, Kokil Jaidka, Thiago A. S. Pardo, Fabrício Benevenuto

Automated news credibility and fact-checking at scale require accurately predicting news factuality and media bias.

Fact Checking Sentence +2

SEMA: an Extended Semantic Evaluation Metric for AMR

1 code implementation • 28 May 2019 • Rafael T. Anchieta, Marco A. S. Cabezudo, Thiago A. S. Pardo

The automatic evaluation of this structure plays an important role in the development of better systems, as well as for semantic annotation.

Sentence

On Strategies of Human Multi-Document Summarization

no code implementations • WS 2015 • Renata Tironi de Camargo, Ariani Di Felippo, Thiago A. S. Pardo

Document Summarization Multi-Document Summarization

Enriching entity grids and graphs with discourse relations: the impact in local coherence evaluation

no code implementations • WS 2015 • M{\'a}rcio de S. Dias, Thiago A. S. Pardo

Coherence Evaluation Question Answering

Joint semantic discourse models for automatic multi-document summarization

no code implementations • WS 2015 • Paula C. Figueira Cardoso, Thiago A. S. Pardo

Document Summarization Multi-Document Summarization

Subtopic Annotation in a Corpus of News Texts: Steps Towards Automatic Subtopic Segmentation

no code implementations • WS 2013 • Paula C. F. Cardoso, Maite Taboada, Thiago A. S. Pardo

Information Retrieval Question Answering