arXiv Open Access 2020

Evaluating German Transformer Language Models with Syntactic Agreement Tests

Karolina Zaczynska Nils Feldhus Robert Schwarzenberg Aleksandra Gabryszak Sebastian Möller
Lihat Sumber

Abstrak

Pre-trained transformer language models (TLMs) have recently refashioned natural language processing (NLP): Most state-of-the-art NLP models now operate on top of TLMs to benefit from contextualization and knowledge induction. To explain their success, the scientific community conducted numerous analyses. Besides other methods, syntactic agreement tests were utilized to analyse TLMs. Most of the studies were conducted for the English language, however. In this work, we analyse German TLMs. To this end, we design numerous agreement tasks, some of which consider peculiarities of the German language. Our experimental results show that state-of-the-art German TLMs generally perform well on agreement tasks, but we also identify and discuss syntactic structures that push them to their limits.

Topik & Kata Kunci

Penulis (5)

K

Karolina Zaczynska

N

Nils Feldhus

R

Robert Schwarzenberg

A

Aleksandra Gabryszak

S

Sebastian Möller

Format Sitasi

Zaczynska, K., Feldhus, N., Schwarzenberg, R., Gabryszak, A., Möller, S. (2020). Evaluating German Transformer Language Models with Syntactic Agreement Tests. https://arxiv.org/abs/2007.03765

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2020
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓