The Chronicles of RAG: The Retriever, the Chunk and the Generator

no code implementations • 15 Jan 2024 • Paulo Finardi, Leonardo Avila, Rodrigo Castaldoni, Pedro Gengo, Celio Larcher, Marcos Piau, Pablo Costa, Vinicius Caridá

Retrieval Augmented Generation (RAG) has become one of the most popular paradigms for enabling LLMs to access external data, and also as a mechanism for grounding to mitigate against hallucinations.

Computational Efficiency Representation Learning +2

UstanceBR: a multimodal language resource for stance prediction

no code implementations • 11 Dec 2023 • Camila Pereira, Matheus Pavan, Sungwon Yoon, Ricelli Ramos, Pablo Costa, Lais Cavalheiro, Ivandre Paraboni

This work introduces UstanceBR, a multimodal corpus in the Brazilian Portuguese Twitter domain for target-based stance prediction.

Personality-dependent Neural Text Summarization

no code implementations • RANLP 2019 • Pablo Costa, Iv Paraboni, r{\'e}

In Natural Language Generation systems, personalization strategies - i. e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results.

Abstractive Text Summarization Text Generation