AIConfPaper
← Search

Max Müller-Eberstein

11 accepted papers

2025

PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs

Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema +1
ICLR 2025poster

The stability of language model pre-training and its effects on downstream performance are still understudied. Prior work shows that the training process can yield significantly different results in response to slight variations in initial conditions, e.g., the random seed. Crucially, the research c…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Can Humans Identify Domains?

Maria Barrett, Max Müller-Eberstein, Elisa Bassignana, Amalie Brogaard Pauli, Mike Zhang, Rob van der Goot
COLING 2024main

Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological property, such as genre, topic, medium or style of a documen…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Enough Is Enough! a Case Study on the Effect of Data Size for Evaluation Using Universal Dependencies

Rob van der Goot, Zoey Liu, Max Müller-Eberstein
COLING 2024main

When creating a new dataset for evaluation, one of the first considerations is the size of the dataset. If our evaluation data is too small, we risk making unsupported claims based on the results on such data. If, on the other hand, the data is too large, we waste valuable annotation time and costs…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Establishing Trustworthiness: Rethinking Tasks and Model Evaluation

Robert Litschko, Max Müller-Eberstein, Rob van der Goot, Leon Weber-Genzel, Barbara Plank
EMNLP 2023short main

Language understanding is a multi-faceted cognitive capability, which the Natural Language Processing (NLP) community has striven to model computationally for decades. Traditionally, facets of linguistic intelligence have been compartmentalized into tasks with specialized model architectures and cor…

Cited by 0Source ↗Scholar ↗
2023

Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training

Max Müller-Eberstein, Rob van der Goot, Barbara Plank, Ivan Titov
EMNLP 2023long findings

Representational spaces learned via language modeling are fundamental to Natural Language Processing (NLP), however there has been limited understanding regarding how and when during training various types of linguistic information emerge and interact. Leveraging a novel information theoretic probin…

Cited by 0Source ↗Scholar ↗
2022

Evidence > Intuition: Transferability Estimation for Encoder Selection

Elisa Bassignana, Max Müller-Eberstein, Mike Zhang, Barbara Plank
EMNLP 2022main

With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori—as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable. However, e…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2022

Experimental Standards for Deep Learning in Natural Language Processing Research

Dennis Ulmer, Elisa Bassignana, Max Müller-Eberstein, Daniel Varab, Mike Zhang, Rob van der Goot +2
EMNLP 2022finding

The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards remains an open challenge to the field at large. Start…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2022

Sort by Structure: Language Model Ranking as Dependency Probing

Max Müller-Eberstein, Rob van der Goot, Barbara Plank
NAACL 2022long

Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored. The field of Computer Vision has begun to tackle encoder ranking, with promising forays into Natural Language Processing, however they lack coverage…

Cited by 3Source ↗PDF ↗Scholar ↗
2021

Genre as Weak Supervision for Cross-lingual Dependency Parsing

Max Müller-Eberstein, Rob van der Goot, Barbara Plank
EMNLP 2021main

Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available, yet remain largely unexplored in cross-lingual setups. We h…

Cited by 27Source ↗PDF ↗code ↗Scholar ↗