Establishing Strong Baselines for TripClick Health Retrieval

01/02/2022
by   Sebastian Hofstätter, et al.
3

We present strong Transformer-based re-ranking and dense retrieval baselines for the recently released TripClick health ad-hoc retrieval collection. We improve the - originally too noisy - training data with a simple negative sampling policy. We achieve large gains over BM25 in the re-ranking task of TripClick, which were not achieved with the original baselines. Furthermore, we study the impact of different domain-specific pre-trained models on TripClick. Finally, we show that dense retrieval outperforms BM25 by considerable margins, even with simple training procedures.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset