Dense X Retrieval: What Retrieval Granularity Should We Use?
- URL: http://arxiv.org/abs/2312.06648v2
- Date: Tue, 12 Dec 2023 03:37:59 GMT
- Title: Dense X Retrieval: What Retrieval Granularity Should We Use?
- Authors: Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran
Zhao, Hongming Zhang, Dong Yu
- Abstract summary: 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. Propositions are defined as atomic expressions within text, each encapsulating a distinct factoid.
Our results reveal that proposition-based retrieval significantly outperforms traditional passage or sentence-based methods in dense retrieval.
- Score: 59.359325855708974
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Dense retrieval has become a prominent method to obtain relevant context or
world knowledge in open-domain NLP tasks. When we use a learned dense retriever
on a retrieval corpus at inference time, an often-overlooked design choice is
the retrieval unit in which the corpus is indexed, e.g. document, passage, or
sentence. We discover that the retrieval unit choice significantly impacts the
performance of both retrieval and downstream tasks. Distinct from the typical
approach of using passages or sentences, we introduce a novel retrieval unit,
proposition, for dense retrieval. Propositions are defined as atomic
expressions within text, each encapsulating a distinct factoid and presented in
a concise, self-contained natural language format. We conduct an empirical
comparison of different retrieval granularity. Our results reveal that
proposition-based retrieval significantly outperforms traditional passage or
sentence-based methods in dense retrieval. Moreover, retrieval by proposition
also enhances the performance of downstream QA tasks, since the retrieved texts
are more condensed with question-relevant information, reducing the need for
lengthy input tokens and minimizing the inclusion of extraneous, irrelevant
information.
Related papers
- Revisiting Sparse Retrieval for Few-shot Entity Linking [33.15662306409253]
We propose an ELECTRA-based keyword extractor to denoise the mention context and construct a better query expression.
For training the extractor, we propose a distant supervision method to automatically generate training data based on overlapping tokens between mention contexts and entity descriptions.
Experimental results on the ZESHEL dataset demonstrate that the proposed method outperforms state-of-the-art models by a significant margin across all test domains.
arXiv Detail & Related papers (2023-10-19T03:51:10Z) - Topic-DPR: Topic-based Prompts for Dense Passage Retrieval [6.265789210037749]
We present Topic-DPR, a dense passage retrieval model that uses topic-based prompts.
We introduce a novel positive and negative sampling strategy, leveraging semi-structured data to boost dense retrieval efficiency.
arXiv Detail & Related papers (2023-10-10T13:45:24Z) - Augmented Embeddings for Custom Retrievals [13.773007276544913]
We introduce Adapted Dense Retrieval, a mechanism to transform embeddings to enable improved task-specific, heterogeneous and strict retrieval.
Dense Retrieval works by learning a low-rank residual adaptation of the pretrained black-box embedding.
arXiv Detail & Related papers (2023-10-09T03:29:35Z) - 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) - BERM: Training the Balanced and Extractable Representation for Matching
to Improve Generalization Ability of Dense Retrieval [54.66399120084227]
We propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM.
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
arXiv Detail & Related papers (2023-05-18T15:43:09Z) - Bridging the Training-Inference Gap for Dense Phrase Retrieval [104.4836127502683]
Building dense retrievers requires a series of standard procedures, including training and validating neural models.
In this paper, we explore how the gap between training and inference in dense retrieval can be reduced.
We propose an efficient way of validating dense retrievers using a small subset of the entire corpus.
arXiv Detail & Related papers (2022-10-25T00:53:06Z) - Phrase Retrieval Learns Passage Retrieval, Too [77.57208968326422]
We study whether phrase retrieval can serve as the basis for coarse-level retrieval including passages and documents.
We show that a dense phrase-retrieval system, without any retraining, already achieves better passage retrieval accuracy.
We also show that phrase filtering and vector quantization can reduce the size of our index by 4-10x.
arXiv Detail & Related papers (2021-09-16T17:42:45Z) - Generation-Augmented Retrieval for Open-domain Question Answering [134.27768711201202]
Generation-Augmented Retrieval (GAR) for answering open-domain questions.
We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy.
GAR achieves state-of-the-art performance on Natural Questions and TriviaQA datasets under the extractive QA setup when equipped with an extractive reader.
arXiv Detail & Related papers (2020-09-17T23:08:01Z) - Progressively Pretrained Dense Corpus Index for Open-Domain Question
Answering [87.32442219333046]
We propose a simple and resource-efficient method to pretrain the paragraph encoder.
Our method outperforms an existing dense retrieval method that uses 7 times more computational resources for pretraining.
arXiv Detail & Related papers (2020-04-30T18:09:50Z)
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.