AI-generated image (Copilot)
Since its inception in 2021, the KEML team has created a series of implementations for various purposes: text2SQL translators, language models predating the advent of large language models, architectures for implementing conversational agents, etc. Here you will find a list of GitHub repositories that illustrate the work already carried out by the group.
More information about these implementations can be obtained on this website, in the Resources menu options, or by contacting the team.
- ArGPT: implementations associated with the creation of the dataset for argumentation, based on large language models. Access here.
- Pirá: implementations associated with the construction and curation of the Pirá dataset: Access here – construction – curation.
- Implementations regarding unsupervised topic analysis using matrix factorization on the Pirá dataset. Access here.
- Framework BLAB: implementations that allow the use of the client-server orchestration architecture of a conversational agent. Access all the codes here.
- BLAB Q&A: implementations associated with a question and answering system about the Blue Amazon, with content extracted from Wikipedia. Access here.
- BLAB Reporter: Implementation for the BLAB Reporter, the journalist robot covering data on the Blue Amazon. Access here.
- Blabinha: Implementation of the Blabinha Framework, a gamified conversational agent focused on the Blue Amazon. Access here.
- Framework dPASP: implementations that enable the use of the framework dPASP – A high-level declarative language for describing sophisticated probabilistic reasoning tasks that can combine perception and logical reasoning. Access here.
- GAP-text2SQL: implementations associated with research on contextual representations for semantic analysis of text-to-SQL. Access here.
- Implementations associated with research on the integration of “question and answering” and “text-to-SQL” in Portuguese. Access here.
- Deepagé: Implementation for the construction of the Deepagé model, a question and answer model about the Brazilian environment. Access here.