THUIR2 at NTCIR-16 Session Search (SS) Task
This work addresses session search for information retrieval researchers, but it is incremental as it applies existing methods to a specific competition task.
The team tackled the NTCIR-16 Session Search Task by using learning-to-rank and fine-tuned pre-trained language models, achieving the best performance in both FOSS and POSS subtasks in preliminary evaluations.
Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task. This paper describes our approaches and results. In the FOSS subtask, we submit five runs using learning-to-rank and fine-tuned pre-trained language models. We fine-tuned the pre-trained language model with ad-hoc data and session information and assembled them by a learning-to-rank method. The assembled model achieves the best performance among all participants in the preliminary evaluation. In the POSS subtask, we used an assembled model which also achieves the best performance in the preliminary evaluation.