Fig. 2: Overview of the proposed sequence-to-sequence approach to document-level joint named entity recognition and relationship extraction task.
From: Structured information extraction from scientific text with large language models
In the first step, lists of JSON documents are prepared from abstracts according to a predefined schema, and the large language model (LLM) is trained. In the second step, this preliminary (intermediate) model is used to accelerate the preparation of additional training data by pre-annotation with the partially trained model and manual correction. An example error is shown highlighted in red. This step may be repeated multiple times with each subsequent partial fine-tuning improving in performance. In the final step, the LLM is fine-tuned on the complete dataset and used for inference to extract desired information from new text.
