Giters

nnstreamer / nntrainer

NNtrainer is Software Framework for Training Neural Network Models on Devices.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Knowledge Embedding Interface Specification for RAG in NNTrainer

hokeun opened this issue · comments

commented

Preliminary research: Pre-training Knowledge Fusion

  • Assume that we describe knowledge as Subject-Predicate-Object (SPO) forms.
  • Delve into and analyze NNTrainer modules that handle user inputs (texts).
  • Decide whether transformation from the knowledge to the input is necessary, and specify transform(or else) logic from the above knowledge to the inputs if needed.
  • Devise a few sample scenarios for Question Answering (QA) to analyze the effects of knowledge embeddings (or prompting).

References

  • AAAI'22 - DKPLM: Decomposable Knowledge-Enhanced Pre-trained Language Model for Natural Language Understanding
  • EMNLP'22 - Knowledge prompting in pre-trained language model for natural language understanding
  • EMNLP'19 - Incorporating External Knowledge into Machine Reading for Generative Question Answering

Disclaimer

NOTE: We're open to suggestions. Please let us know in the comments if you have any feedback or guidance!

commented

:octocat: cibot: Thank you for posting issue #2519. The person in charge will reply soon.

commented

Thanks for bringing this topic to NNTrainer. We are happy to help.