212 citations · 741 across the 81 of their papers we have counts for
11 papers · 2 filters
Understanding and Mitigating Classification Errors Through Interpretable Token Patterns
Michael A. Hedderich, Jonas Fischer, Dietrich Klakow +1
State-of-the-art NLP methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight int…
Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures
Julius Steuer, Marius Mosbach, Dietrich Klakow
Research on the cognitive plausibility of language models (LMs) has so far mostly concentrated on modelling psycholinguistic response variables such as reading times, gaze duration…
A Lightweight Method to Generate Unanswerable Questions in English
Vagrant Gautam, Miaoran Zhang, Dietrich Klakow
If a question cannot be answered with the available information, robust systems for question answering (QA) should know _not_ to answer. One way to build QA models that do this is…
Information-Theoretic Characterization of Vowel Harmony: A Cross-Linguistic Study on Word Lists
Julius Steuer, Badr Abdullah, Johann-Mattis List +1
We present a cross-linguistic study that aims to quantify vowel harmony using data-driven computational modeling. Concretely, we define an information-theoretic measure of harmonic…
On the N-gram Approximation of Pre-trained Language Models
Aravind Krishnan, Jesujoba Alabi, Dietrich Klakow
Large pre-trained language models (PLMs) have shown remarkable performance across various natural language understanding (NLU) tasks, particularly in low-resource settings. Neverth…
An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech
Badr M. Abdullah, Mohammed Maqsood Shaik, Bernd Möbius +1
Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to cha…
Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
Marius Mosbach, Tiago Pimentel, Shauli Ravfogel +2
Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity…
MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Cheikh M. Bamba Dione, David Adelani, Peter Nabende +41
In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these…
Weaker Than You Think: A Critical Look at Weakly Supervised Learning
Dawei Zhu, Xiaoyu Shen, Marius Mosbach +2
Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it…
KÚ <MASK>: Integrating Yorùbá cultural greetings into machine translation
Idris Akinade, Jesujoba Alabi, David Adelani +2
This paper investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yorùbá greetings ( kú [MASK]), which are a bi…
Analyzing the Representational Geometry of Acoustic Word Embeddings
Badr M. Abdullah, Dietrich Klakow
Acoustic word embeddings (AWEs) are vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding space. In addition to their…