Generative Retrieval as Multi-Vector Dense Retrieval
- URL: http://arxiv.org/abs/2404.00684v1
- Date: Sun, 31 Mar 2024 13:29:43 GMT
- Title: Generative Retrieval as Multi-Vector Dense Retrieval
- Authors: Shiguang Wu, Wenda Wei, Mengqi Zhang, Zhumin Chen, Jun Ma, Zhaochun Ren, Maarten de Rijke, Pengjie Ren,
- Abstract summary: Generative retrieval generates identifiers of relevant documents in an end-to-end manner.
Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval.
We show that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document.
- Score: 71.75503049199897
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between generative retrieval and other retrieval methods, especially those based on matching within dense retrieval models, is not yet fully comprehended. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. Accordingly, generative retrieval exhibits behavior analogous to hierarchical search within a tree index in dense retrieval when using hierarchical semantic identifiers. However, prior work focuses solely on the retrieval stage without considering the deep interactions within the decoder of generative retrieval. In this paper, we fill this gap by demonstrating that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document. Specifically, we examine the attention layer and prediction head of generative retrieval, revealing that generative retrieval can be understood as a special case of multi-vector dense retrieval. Both methods compute relevance as a sum of products of query and document vectors and an alignment matrix. We then explore how generative retrieval applies this framework, employing distinct strategies for computing document token vectors and the alignment matrix. We have conducted experiments to verify our conclusions and show that both paradigms exhibit commonalities of term matching in their alignment matrix.
Related papers
- Query-oriented Data Augmentation for Session Search [71.84678750612754]
We propose query-oriented data augmentation to enrich search logs and empower the modeling.
We generate supplemental training pairs by altering the most important part of a search context.
We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty.
arXiv Detail & Related papers (2024-07-04T08:08:33Z) - Dense X Retrieval: What Retrieval Granularity Should We Use? [56.90827473115201]
Often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence.
We introduce a novel retrieval unit, proposition, for dense retrieval.
Experiments reveal that indexing a corpus by fine-grained units such as propositions significantly outperforms passage-level units in retrieval tasks.
arXiv Detail & Related papers (2023-12-11T18:57:35Z) - Lexically-Accelerated Dense Retrieval [29.327878974130055]
'LADR' (Lexically-Accelerated Dense Retrieval) is a simple-yet-effective approach that improves the efficiency of existing dense retrieval models.
LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks.
arXiv Detail & Related papers (2023-07-31T15:44:26Z) - Recommender Systems with Generative Retrieval [58.454606442670034]
We propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates.
To that end, we create semantically meaningful of codewords to serve as a Semantic ID for each item.
We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets.
arXiv Detail & Related papers (2023-05-08T21:48:17Z) - CAPSTONE: Curriculum Sampling for Dense Retrieval with Document
Expansion [68.19934563919192]
We propose a curriculum sampling strategy that utilizes pseudo queries during training and progressively enhances the relevance between the generated query and the real query.
Experimental results on both in-domain and out-of-domain datasets demonstrate that our approach outperforms previous dense retrieval models.
arXiv Detail & Related papers (2022-12-18T15:57:46Z) - Generate-and-Retrieve: use your predictions to improve retrieval for
semantic parsing [25.725176422936766]
We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar.
GandR first generates a preliminary prediction with input-based retrieval.
Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction.
arXiv Detail & Related papers (2022-09-29T16:03:29Z) - Autoregressive Search Engines: Generating Substrings as Document
Identifiers [53.0729058170278]
Autoregressive language models are emerging as the de-facto standard for generating answers.
Previous work has explored ways to partition the search space into hierarchical structures.
In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
arXiv Detail & Related papers (2022-04-22T10:45:01Z) - CODER: An efficient framework for improving retrieval through
COntextualized Document Embedding Reranking [11.635294568328625]
We present a framework for improving the performance of a wide class of retrieval models at minimal computational cost.
It utilizes precomputed document representations extracted by a base dense retrieval method.
It incurs a negligible computational overhead on top of any first-stage method at run time, allowing it to be easily combined with any state-of-the-art dense retrieval method.
arXiv Detail & Related papers (2021-12-16T10:25:26Z) - Improving Document Representations by Generating Pseudo Query Embeddings
for Dense Retrieval [11.465218502487959]
We design a method to mimic the queries on each of the documents by an iterative clustering process.
We also optimize the matching function with a two-step score calculation procedure.
Experimental results on several popular ranking and QA datasets show that our model can achieve state-of-the-art results.
arXiv Detail & Related papers (2021-05-08T05:28:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.