Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Zero-Shot Cross-Lingual Transfer is a Hard Baseline to Beat in German Fine-Grained Entity Typing

Publication

Zero-Shot Cross-Lingual Transfer is a Hard Baseline to Beat in German Fine-Grained Entity Typing

Weber, Sabine; Steedman, Mark (2025): Zero-Shot Cross-Lingual Transfer is a Hard Baseline to Beat in German Fine-Grained Entity Typing, in: Bamberg: Otto-Friedrich-Universität, S. 42–48.

Details

Faculty/Chair
Faculty/Professorship
Author
Steedman, Mark
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2025
Source/Other editions
João Sedoc, Anna Rogers, Anna Rumshisky, u. a. (Hrsg.), Proceedings of the Second Workshop on Insights from Negative Results in NLP, Association for Computational Linguistics, 2021, S. 42–48
Year of first publication
2021
Language
English
Licence
URN
Abstract

The training of NLP models often requires large amounts of labelled training data, which makes it difficult to expand existing models to new languages. While zero-shot cross-lingual transfer relies on multilingual word embeddings to apply a model trained on one language to another, Yarowski and Ngai (2001) propose the method of annotation projection to generate training data without manual annotation. This method was successfully used for the tasks of named entity recognition and coarse-grained entity typing, but we show that it is outperformed by zero-shot cross-lingual transfer when applied to the similar task of fine-grained entity typing. In our study of fine-grained entity typing with the FIGER type ontology for German, we show that annotation projection amplifies the English model’s tendency to underpredict level 2 labels and is beaten by zero-shot cross-lingual transfer on three novel test sets.

Keywords
Zero-Shot Cross-Lingual Transfer
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2025-11-10

Permalink: https://fis.uni-bamberg.de/handle/uniba/110856 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.