Phrase Retrieval Learns Passage Retrieval, Too

By Jinhyuk Lee, Alexander Wettig, Danqi Chen. 2021

50 citations recorded by the source corpus.

Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval—the most fine-grained retrieval unit—is appealing because phrases can be directly used as the output for question answering and slot filling tasks. In this work, we follow the intuition that retrieving phrases naturally entails retrieving larger text blocks and study whether phrase retrieval can serve as the basis for coarse-level retrieval including passages and documents. We first observe that a dense phrase-retrieval system, without any retraining, already achieves better passage retrieval accuracy (+3-5% in top-5 accuracy) compared to passage retrievers, which also helps achieve superior end-to-end QA performance with fewer passages. Then, we provide an interpretation for why phrase-level supervision helps learn better fine-grained entailment compared to passage-level supervision, and also show that phrase retrieval can be improved to achieve competitive performance in document-retrieval tasks such as entity linking and knowledge-grounded dialogue. Finally, we demonstrate how phrase filtering and vector quantization can reduce the size of our index by 4-10x, making dense phrase retrieval a practical and versatile solution in multi-granularity retrieval.

Subfields: Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

1. Luyu Gao
2. Sebastian Riedel
3. Wen-tau Yih
4. Jamie Callan
5. Jing Liu
6. Ruiyang Ren
7. Ji-rong Wen
8. Wayne Xin Zhao

Citations in the corpus

• You Only Need One Model for Open-domain Question Answering (2021, methodology): “Per-token embeddings or multiple embeddings were used in ColBERT (Khattab et al., 2020), ME-BERT (Luan et al., 2021), Lin et al. (2021), Lee et al. (2021).”
• Learning to Retrieve Passages without Supervision (2021, background): “Lee et al. (2021a) demonstrated strong end-to-end ODQA results with this approach, and Lee et al. (2021b) showed that it is also effective for passage retrieval.”
• Domain-matched Pre-training Tasks for Dense Retrieval (2021, background): “Encoding each passage with multiple vectors, based on dense phrase representations, has also been proposed and shown good retrieval accuracy (Lee et al., 2021).”
• Dense Text Retrieval Based on Pretrained Language Models: A Survey (2022, background): “An interesting observation found in [181] is that a dense phrase retrieval system can achieve a better passage retrieval accuracy than DPR on NQ and TriviaQA, without any retraining.”
• Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer (2022, methodology): “We compare retrieval performance with lexical models BM25 (Robertson and Zaragoza, 2009), passage-level dense retrievers DPR, ANCE, coCon-denser, FiD-KD, YONO (with and without retrieval pretraining) (Karpukhin et al., 2020; Oguz et al., 2021; Xiong et al., 2021; Gao and Callan, 2022; Izacard and Gr”