Papers by Hugo Gonçalo Oliveira
Towards Generation and Recognition of Humorous Texts in Portuguese (2023.eacl-srw)
Copied to clipboard
| Challenge: | This PhD thesis focuses on the automatic generation and recognition of verbal punning humor in Portuguese. |
| Approach: | They propose to combine natural language generation and cognitive processing to generate and recognize verbal humor in Portuguese. |
| Outcome: | The proposed methods aim to generate and recognize humor in Portuguese, an underdeveloped language compared to English. |
A Brief Survey of Textual Dialogue Corpora (2022.lrec-1)
Copied to clipboard
| Challenge: | Several dialogue corpora are available for research purposes, but they do not cover all the necessities of real-world applications. |
| Approach: | They analyze available dialogue corpora and propose possible approaches to create new ones. |
| Outcome: | The proposed corpus of human-human dialogues is based on a list of available dialogue corpora . it covers speakers, size, languages, collection, annotations, and domains . some trends are identified and possible approaches are also discussed . |
Exploring Transformers for Ranking Portuguese Semantic Relations (2022.lrec-1)
Copied to clipboard
| Challenge: | Using transformers, we rank instances of Portuguese lexico-semantic relations . despite the negative results, we see the reported experiments as another contribution for better understanding transformer-based language models like BERT and GPT. |
| Approach: | They investigated transformer-based language models for ranking instances of Portuguese lexico-semantic relations using weights based on likelihood of natural language sequences that transmitted the relation instances. |
| Outcome: | The proposed models are not correlated with redundancy, but lower for instances with longer and more specific arguments, and not useful when computing word similarity with network embeddings. |
Corpora and Baselines for Humour Recognition in Portuguese (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on the recognition of verbal humour in Portuguese has not been done . humor recognition is a sign of fluency in a language, and is not yet widely used in other languages. |
| Approach: | They propose to create three corpora covering two styles of humour and four sources of non-humorous text that are used for testing computational models. |
| Outcome: | The proposed models can be used to train and test models in Portuguese, and may be used as baselines for future projects. |
AIA-BDE: A Corpus of FAQs in Portuguese and their Variations (2020.lrec-1)
Copied to clipboard
Hugo Gonçalo Oliveira, João Ferreira, José Santos, Pedro Fialho, Ricardo Rodrigues, Luisa Coheur, Ana Alves
| Challenge: | a corpus of 380 domain-oriented FAQs in Portuguese is presented . paraphrases or entailed questions are created manually, by humans, or automatically, with Google Translate. |
| Approach: | They present a corpus of 380 domain-oriented FAQs in Portuguese and their variations, i.e., paraphrases or entailed questions, created manually, by humans, or automatically, with Google Translate. |
| Outcome: | The proposed system outperforms other systems in the domain of question-answering . it performs well when matching variations with their original questions . |