The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines

no code implementations • 22 Jan 2024 • Martina Forster, Claudia Schulz, Prudhvi Nokku, Melicaalsadat Mirsafian, Jaykumar Kasundra, Stavroula Skylaki

Multi-Label Classification (MLC) is a common task in the legal domain, where more than one label may be assigned to a legal document.

Multi-Label Classification

Context-Aware Classification of Legal Document Pages

no code implementations • 5 Apr 2023 • Pavlos Fragkogiannis, Martina Forster, Grace E. Lee, Dell Zhang

For many business applications that require the processing, indexing, and retrieval of professional documents such as legal briefs (in PDF format etc.

Classification Document Image Classification +1

Determinantal Beam Search

no code implementations • ACL 2021 • Clara Meister, Martina Forster, Ryan Cotterell

Beam search is a go-to strategy for decoding neural sequence models.

Point Processes Text Generation

Searching for Search Errors in Neural Morphological Inflection

no code implementations • EACL 2021 • Martina Forster, Clara Meister, Ryan Cotterell

Yet, on word-level tasks, exact inference of these models reveals the empty string is often the global optimum.

Morphological Inflection Text Generation

SIGMORPHON 2020 Task 0 System Description: ETH Z\"urich Team

no code implementations • WS 2020 • Martina Forster, Clara Meister

This paper presents our system for the SIGMORPHON 2020 Shared Task.

Machine Translation Morphological Inflection +2