Papers by Viviane Moreira
A Large Parallel Corpus of Full-Text Scientific Articles (L18-1)
Copied to clipboard
| Challenge: | Scielo database contains articles from several research domains. |
| Approach: | They propose to build a parallel corpus from Scielo in three languages: English, Portuguese, and Spanish. |
| Outcome: | The proposed system outperforms other systems on scientific articles in English, Portuguese, and Spanish. |
Offensive Video Detection: Dataset and Baseline Results (2020.lrec-1)
Copied to clipboard
| Challenge: | a large number of social media platforms discourage users from publishing offensive content . however, there is no method to detect offensive content on these platforms due to the high volume of publications. |
| Approach: | They propose to use text-based machine learning to detect offensive content on different platforms . they use word embedding with Deep Learning classifiers to perform best results . |
| Outcome: | The proposed methods outperform Classic and Deep Learning classifiers in Portuguese and CNN architectures in other features. |
Embeddings for Named Entity Recognition in Geoscience Portuguese Literature (2020.lrec-1)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a task within the field of Natural Language Processing that deals with the identification and categorization of Named entities (NEs) in a given text. |
| Approach: | They propose to use vector and tensor embeddings to train Portuguese Named Entity Recognition (NER) in the Geology domain. |
| Outcome: | The proposed model achieves state-of-the-art for the Portuguese Geology domain with one of its embeddings. |
Evaluation of Question Answer Generation for Portuguese: Insights and Datasets (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Automatic question generation is an increasingly important task that can be applied in educational settings, data augmentation for question-answering (QA), and conversational systems. |
| Approach: | They adapt and apply QAG approaches to generate question-answer pairs given context and look into strategies for error filtering and their effects. |
| Outcome: | The proposed methods can generate question-answer pairs in Portuguese, a widely spoken language that is underrepresented in natural language processing research. |
InferBR: A Natural Language Inference Dataset in Portuguese (2024.lrec-main)
Copied to clipboard
| Challenge: | Portuguese has few NLI-annotated datasets created through automatic translation followed by manual checking. |
| Approach: | They propose to generate premises and hypotheses using a semiautomatic process to generate sentences and manually check the annotations. |
| Outcome: | The proposed dataset is better at recognizing entailment classes in other Portuguese datasets than the reverse. |