8 papers
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Xiao Wang, Sean MacAvaney, Craig Macdonald
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Metho…
Pipeline Inspection, Visualization, and Interoperability in PyTerrier
Emmanouil Georgios Lionis, Craig Macdonald, Sean MacAvaney
PyTerrier provides a declarative framework for building and experimenting with Information Retrieval (IR) pipelines. In this demonstration, we highlight several recent pipeline ope…
To Case or Not to Case: An Empirical Study in Learned Sparse Retrieval
Emmanouil Georgios Lionis, Jia-Huei Ju, Angelos Nalmpantis +3
Learned Sparse Retrieval (LSR) methods construct sparse lexical representations of queries and documents that can be efficiently searched using inverted indexes. Existing LSR appro…
Lost in Transliteration: Bridging the Script Gap in Neural IR
Andreas Chari, Iadh Ounis, Sean MacAvaney
Most human languages use scripts other than the Latin alphabet. Search users in these languages often formulate their information needs in a transliterated -- usually Latinized --…
Artifact Sharing for Information Retrieval Research
Sean MacAvaney
Sharing artifacts -- such as trained models, pre-built indexes, and the code to use them -- aids in reproducibility efforts by allowing researchers to validate intermediate steps a…
GRIT: Graph-based Recall Improvement for Task-oriented E-commerce Queries
Hrishikesh Kulkarni, Surya Kallumadi, Sean MacAvaney +2
Many e-commerce search pipelines have four stages, namely: retrieval, filtering, ranking, and personalized-reranking. The retrieval stage must be efficient and yield high recall be…