Papers by Helena Caseli

4 papers
Choosing What to Mask: More Informed Masking for Multimodal Machine Translation (2023.acl-srw)

Copied to clipboard

Challenge: Pre-trained language models have achieved remarkable results on several NLP tasks.
Approach: They propose three new masking strategies for cross-lingual visual pre-training that focus on learning different linguistic patterns.
Outcome: The proposed methods outperform the baseline model and achieve state-of-the-art accuracy on the Portuguese-English MMT task.
Identifying Fine-grained Depression Signs in Social Media Posts (2024.lrec-main)

Copied to clipboard

Challenge: Currently, most studies focus on a binary classification setup or on pre-established resources.
Approach: They evaluated machine learning techniques to model 21 depression signs in social media posts from Brazilian undergraduate students.
Outcome: The proposed methods struggle to classify the majority of depression signs on social media posts, compared with the majority on the social media sites.
NMT and PBSMT Error Analyses in English to Brazilian Portuguese Automatic Translations (2020.lrec-1)

Copied to clipboard

Challenge: Recent work proposes neural machine translation (NMT) for Brazilian Portuguese.
Approach: They propose a neural machine translation approach that generates equivalent sentences in target language and source language.
Outcome: The proposed approach outperforms phrase-based statistical machine translation systems for some pairs of languages.
Multilingual and Multimodal Learning for Brazilian Portuguese (2022.lrec-1)

Copied to clipboard

Challenge: Existing models that learn multimodal and multilingual representations perform better in many natural language tasks.
Approach: They use a multimodal and multilingual corpus to test its generalization ability for other languages . they achieve a BLEU score of 51.8 and a METEOR score of 78.0 on the test set .
Outcome: The proposed model outperforms the existing model on a Portuguese-English multimodal translation task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations