Establishing Strong Baselines for TripClick Health Retrieval

We present strong Transformer-based re-ranking and <PRE_TAG>dense retrieval</POST_TAG> 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 <PRE_TAG>dense retrieval</POST_TAG> outperforms BM25 by considerable margins, even with simple training procedures.