Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

01/25/2022
by   Tao Chen, et al.
0

The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to generalize a deep retrieval model to other tasks and domains. In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting. Our findings show that the performance of a deep retrieval model is significantly deteriorated when the target domain is very different from the source domain that the model was trained on. On the contrary, lexical models are more robust across domains. We thus propose a simple yet effective framework to integrate lexical and deep retrieval models. Our experiments demonstrate that these two models are complementary, even when the deep model is weaker in the out-of-domain setting. The hybrid model obtains an average of 20.4 of 9.54

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2022

Improving Passage Retrieval with Zero-Shot Question Generation

We propose a simple and effective re-ranking method for improving passag...
research
12/20/2022

HYRR: Hybrid Infused Reranking for Passage Retrieval

We present Hybrid Infused Reranking for Passages Retrieval (HYRR), a fra...
research
07/19/2023

SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval

Traditionally, sparse retrieval systems relied on lexical representation...
research
09/22/2020

Embedding-based Zero-shot Retrieval through Query Generation

Passage retrieval addresses the problem of locating relevant passages, u...
research
10/21/2022

An Analysis of Fusion Functions for Hybrid Retrieval

We study hybrid search in text retrieval where lexical and semantic sear...
research
04/27/2023

Large Language Models are Strong Zero-Shot Retriever

In this work, we propose a simple method that applies a large language m...
research
05/26/2021

Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics

Medical entity retrieval is an integral component for understanding and ...

Please sign up or login with your details

Forgot password? Click here to reset