I^3 Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval
Preprint
Abstract
Passage retrieval is a fundamental task in many information systems, such as web search and question answering, where both efficiency and effectiveness are critical concerns. In recent years, neural retrievers based on pre-trained language models (PLM), such as dual-encoders, have achieved huge success. Yet, studies have found that the performance of dual-encoders are often limited due to the neglecting of the interaction information between queries and candidate passages. Therefore, various interaction paradigms have been proposed to improve the performance of vanilla dual-encoders. Particularly, recent state-of-the-art methods often introduce late-interaction during the model inference process. However, such late-interaction based methods usually bring extensive computation and storage cost on large corpus. Despite their effectiveness, the concern of efficiency and space footprint is still an important factor that limits the application of interaction-based neural retrieval models. To tackle this issue, we incorporate implicit interaction into dual-encoders, and propose I^3 retriever. In particular, our implicit interaction paradigm leverages generated pseudo-queries to simulate query-passage interaction, which jointly optimizes with query and passage encoders in an end-to-end manner. It can be fully pre-computed and cached, and its inference process only involves simple dot product operation of the query vector and passage vector, which makes it as efficient as the vanilla dual encoders. We conduct comprehensive experiments on MSMARCO and TREC2019 Deep Learning Datasets, demonstrating the I^3 retriever's superiority in terms of both effectiveness and efficiency. Moreover, the proposed implicit interaction is compatible with special pre-training and knowledge distillation for passage retrieval, which brings a new state-of-the-art performance.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders Are Better Dense Retrievers2023
- SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval2023
- Constructing Tree-based Index for Efficient and Effective Dense Retrieval2023
- Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking2022
- Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction2022
- Disentangled Graph Recurrent Network for Document RankingData Science and Engineering, 2022
- Pre-trained Language Model for Web-scale Retrieval in Baidu Search2021
- A Deep Look into neural ranking models for information retrievalInformation Processing & Management, 2020
- Billion-Scale Similarity Search with GPUsIEEE Transactions on Big Data, 2019
- Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information RetrievalIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016