Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bönisch, Kevin, Mehler, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917887677038592
author Bönisch, Kevin
Mehler, Alexander
author_facet Bönisch, Kevin
Mehler, Alexander
contents We introduce a retrieval approach leveraging Support Vector Regression (SVR) ensembles, bootstrap aggregation (bagging), and embedding spaces on the German Dataset for Legal Information Retrieval (GerDaLIR). By conceptualizing the retrieval task in terms of multiple binary needle-in-a-haystack subtasks, we show improved recall over the baselines (0.849 > 0.803 | 0.829) using our voting ensemble, suggesting promising initial results, without training or fine-tuning any deep learning models. Our approach holds potential for further enhancement, particularly through refining the encoding models and optimizing hyperparameters.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles
Bönisch, Kevin
Mehler, Alexander
Information Retrieval
Artificial Intelligence
We introduce a retrieval approach leveraging Support Vector Regression (SVR) ensembles, bootstrap aggregation (bagging), and embedding spaces on the German Dataset for Legal Information Retrieval (GerDaLIR). By conceptualizing the retrieval task in terms of multiple binary needle-in-a-haystack subtasks, we show improved recall over the baselines (0.849 > 0.803 | 0.829) using our voting ensemble, suggesting promising initial results, without training or fine-tuning any deep learning models. Our approach holds potential for further enhancement, particularly through refining the encoding models and optimizing hyperparameters.
title Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2501.05018