Multi-Vector Retrieval as Sparse Alignment

by   Yujie Qian, et al.

Multi-vector retrieval models improve over single-vector dual encoders on many information retrieval tasks. In this paper, we cast the multi-vector retrieval problem as sparse alignment between query and document tokens. We propose AligneR, a novel multi-vector retrieval model that learns sparsified pairwise alignments between query and document tokens (e.g. `dog' vs. `puppy') and per-token unary saliences reflecting their relative importance for retrieval. We show that controlling the sparsity of pairwise token alignments often brings significant performance gains. While most factoid questions focusing on a specific part of a document require a smaller number of alignments, others requiring a broader understanding of a document favor a larger number of alignments. Unary saliences, on the other hand, decide whether a token ever needs to be aligned with others for retrieval (e.g. `kind' from `kind of currency is used in new zealand'). With sparsified unary saliences, we are able to prune a large number of query and document token vectors and improve the efficiency of multi-vector retrieval. We learn the sparse unary saliences with entropy-regularized linear programming, which outperforms other methods to achieve sparsity. In a zero-shot setting, AligneR scores 51.1 points nDCG@10, achieving a new retriever-only state-of-the-art on 13 tasks in the BEIR benchmark. In addition, adapting pairwise alignments with a few examples (<= 8) further improves the performance up to 15.7 points nDCG@10 for argument retrieval tasks. The unary saliences of AligneR helps us to keep only 20 the document token representations with minimal performance loss. We further show that our model often produces interpretable alignments and significantly improves its performance when initialized from larger language models.


Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

Multi-vector retrieval models such as ColBERT [Khattab and Zaharia, 2020...

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary

Dual encoders are now the dominant architecture for dense retrieval. Yet...

CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval

Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) ...

Referral Augmentation for Zero-Shot Information Retrieval

We propose Referral-Augmented Retrieval (RAR), a simple technique that c...

Sparse, Dense, and Attentional Representations for Text Retrieval

Dual encoder architectures perform retrieval by encoding documents and q...

Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction

Recent progress in neural information retrieval has demonstrated large g...

An Efficiency Study for SPLADE Models

Latency and efficiency issues are often overlooked when evaluating IR mo...

Please sign up or login with your details

Forgot password? Click here to reset