George Zerveas, Navid Rekabsaz, Carsten Eickhoff,
"Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors"
: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 12-2023
Original Titel:
Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Original Kurzfassung:
Sparse annotation poses persistent challenges to training dense retrieval models, for example by distorting the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this
problem, we introduce evidence-based label smoothing, a novel, computationally efficient method that prevents penalizing the model for assigning high relevance to false negatives. To compute the target relevance distribution over candidate documents within the ranking context of a given
query, those candidates most similar to the ground truth are assigned a non-zero relevance probability based on the degree of their similarity to the ground-truth document(s). To estimate relevance we leverage an improved similarity metric based on reciprocal nearest neighbors, which
can also be used independently to rerank candidates in post-processing. Through extensive experiments on two large-scale ad hoc text retrieval datasets, we demonstrate that reciprocal nearest neighbors can improve the ranking effectiveness of dense retrieval models, both when used for
label smoothing, as well as for reranking. This indicates that by considering relationships between documents and queries beyond simple geometric distance we can effectively enhance the ranking context.
Forschungs-