I’ve been considering an LLM API, and it definitely sounds promising. My main concern is the cost—I'm processing around 300 job offers per day and plan to scale up further. Do you have any go-to APIs you’d recommend that balance performance and pricing?
Do you think SBERT + SVM is a good fit for handling ambiguous or less common phrases, or do you still end up needing some post-processing rules for edge cases?
I’ve been sticking with PhraseMatcher because it’s simple, fast, and predictable—but your suggestion about using smaller BERT-based models or embeddings like SBERT (sentence-transformers) is intriguing. I’ve avoided LLMs so far because of the computational overhead, but it sounds like even lightweight models can provide significant value.
Out of curiosity, when training models like SBERT or even smaller BERT versions, do you see diminishing returns when working with smaller training sets (e.g., a few thousand annotated job descriptions)? My current dataset isn’t huge yet (10k), so I wonder where that line starts to appear.
I’ll definitely look more into SBERT and segmentation approaches—thanks for sharing those!