Help Privacy Policy Disclaimer
  Advanced SearchBrowse





CEQE: Contextualized Embeddings for Query Expansion


Yates,  Andrew
Databases and Information Systems, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (public)

(Preprint), 189KB

Supplementary Material (public)
There is no public supplementary material available

Naseri, S., Dalton, J., Yates, A., & Allan, J. (2021). CEQE: Contextualized Embeddings for Query Expansion. Retrieved from https://arxiv.org/abs/2103.05256.

Cite as: http://hdl.handle.net/21.11116/0000-0009-6779-C
In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We propose a new model, Contextualized Embeddings for Query Expansion (CEQE), that utilizes query-focused contextualized embedding vectors. We study the behavior of contextual representations generated for query expansion in ad-hoc document retrieval. We conduct our experiments on probabilistic retrieval models as well as in combination with neural ranking models. We evaluate CEQE on two standard TREC collections: Robust and Deep Learning. We find that CEQE outperforms static embedding-based expansion methods on multiple collections (by up to 18% on Robust and 31% on Deep Learning on average precision) and also improves over proven probabilistic pseudo-relevance feedback (PRF) models. We further find that multiple passes of expansion and reranking result in continued gains in effectiveness with CEQE-based approaches outperforming other approaches. The final model incorporating neural and CEQE-based expansion score achieves gains of up to 5% in P@20 and 2% in AP on Robust over the state-of-the-art transformer-based re-ranking model, Birch.