Establishing Strong Baselines for TripClick Health Retrieval
This work provides incremental improvements for health information retrieval by establishing stronger baselines on a specific dataset.
The authors tackled the problem of improving retrieval performance on the TripClick health collection by developing Transformer-based re-ranking and dense retrieval baselines, achieving large gains over BM25 with simple training enhancements.
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.