Conformer-Kernel with Query Term Independence at TREC 2020 Deep Learning Track
This work addresses retrieval quality for information retrieval systems, but it is incremental as it builds on existing models and benchmarks.
The paper tackled the problem of improving retrieval quality in the TREC 2020 Deep Learning track by benchmarking Conformer-Kernel models with strategies like explicit term matching, query term independence, and using ORCAS click data, finding that these strategies led to improved retrieval quality.
We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track. In particular, we study the impact of incorporating: (i) Explicit term matching to complement matching based on learned representations (i.e., the "Duet principle"), (ii) query term independence (i.e., the "QTI assumption") to scale the model to the full retrieval setting, and (iii) the ORCAS click data as an additional document description field. We find evidence which supports that all three aforementioned strategies can lead to improved retrieval quality.