I first posted a question in Mapping relationships between named entities and unlabeled spans, which @SofieVL was kind enough to answer and helped clarify my questions. I'm starting a more focused topic here because I think it might be useful for the community.
First, as with NER, can we leverage pretrained word vectors for spancat? And can spancat be adapted to work with transformers models? (Adapting data labeled in prodigy to a compatible format for NER was just a simple shift to IOB tags...)
Assuming spancat is the best option for us, given that we have overlapping entities, we have two types of relationship use cases we'd like to replicate. In the first type, one span is overlapping with another.
In the second, the spans are separated
It seems like the relationship extraction recipe could allow us to label the relationships between body locations and other labels where they are separated. Overlapping spans wouldn't show up, but where spans are overlapping shouldn't require a model anyway. Having not modeled relationships before, I'm just trying to validate my assumptions here; any feedback would be appreciated.