Treffer: Few-Shot Legal Text Segmentation via Rewiring Conditional Random Fields: A Preliminary Study
Title:
Few-Shot Legal Text Segmentation via Rewiring Conditional Random Fields: A Preliminary Study
Authors:
Contributors:
Ferrara, A., Picascia, S., Riva, D.
Publisher Information:
Springer Science and Business Media Deutschland
Publication Year:
2023
Collection:
PORTO@iris (Publications Open Repository TOrino - Politecnico di Torino)
Subject Terms:
Document Type:
Konferenz
conference object
Language:
English
Relation:
info:eu-repo/semantics/altIdentifier/isbn/9783031471117; info:eu-repo/semantics/altIdentifier/isbn/9783031471124; ispartofbook:Advances in Conceptual Modeling; ER 2023 Workshops, CMLS, CMOMM4FAIR, EmpER, JUSMOD, OntoCom, QUAMES, and SmartFood; volume:14319; firstpage:141; lastpage:150; numberofpages:10; serie:LECTURE NOTES IN COMPUTER SCIENCE; https://hdl.handle.net/11583/2992892
DOI:
10.1007/978-3-031-47112-4_13
Availability:
Rights:
info:eu-repo/semantics/openAccess ; license:Pubblico - Tutti i diritti riservati ; license:Non Pubblico - Accesso privato/ristretto ; license uri:iris.PUB01 ; license uri:iris.PRI01
Accession Number:
edsbas.9A79FBA1
Database:
BASE
Weitere Informationen
Functional Text Segmentation is the task of partitioning a textual document in segments that play a certain function. In the legal domain, this is important to support downstream tasks, but it faces also challenges of segment discontinuity, few-shot scenario, and domain specificity. We propose an approach that, revisiting the underlying graph structure of a Conditional Random Field and relying on a combination of neural embeddings and engineered features, is capable of addressing these challenges. Evaluation on a dataset of Italian case law decisions yields promising results.