SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries
This addresses a specific bottleneck in retrieval systems for logic-structured queries, offering a domain-specific incremental improvement.
The paper tackled the problem of poor retrieval performance for Boolean logic and set operation queries by introducing SetBERT, a fine-tuned BERT-based model, which achieved up to a 63% improvement in Recall and matched the performance of larger models while being smaller.
We introduce SetBERT, a fine-tuned BERT-based model designed to enhance query embeddings for set operations and Boolean logic queries, such as Intersection (AND), Difference (NOT), and Union (OR). SetBERT significantly improves retrieval performance for logic-structured queries, an area where both traditional and neural retrieval methods typically underperform. We propose an innovative use of inversed-contrastive loss, focusing on identifying the negative sentence, and fine-tuning BERT with a dataset generated via prompt GPT. Furthermore, we demonstrate that, unlike other BERT-based models, fine-tuning with triplet loss actually degrades performance for this specific task. Our experiments reveal that SetBERT-base not only significantly outperforms BERT-base (up to a 63% improvement in Recall) but also achieves performance comparable to the much larger BERT-large model, despite being only one-third the size.