Search Results for author:
Found 14 papers, 10 papers with code
A Cross-lingual Comparison of Human and Model Relative Word Importance
Relative word importance is a key metric for natural language processing.
Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs
Instruction-finetuned Large Language Models inherit clear political leanings that have been shown to influence downstream task performance.
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations
Rationales in the form of manually annotated input spans usually serve as ground truth when evaluating explainability methods in NLP.
Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models
We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models.
On the Interplay between Fairness and Explainability
In order to build reliable and trustworthy NLP applications, models need to be both fair across different demographics and explainable.
Rather a Nurse than a Physician -- Contrastive Explanations under Investigation
A cross-comparison between model-based rationales and human annotations, both in contrastive and non-contrastive settings, yields a high agreement between the two settings for models as well as for humans.
WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset
We present WebQAmGaze, a multilingual low-cost eye-tracking-while-reading dataset, designed as the first webcam-based eye-tracking corpus of reading to support the development of explainable computational language processing models.
Domain-Specific Word Embeddings with Structure Prediction
Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, e. g., across time or domain.
Every word counts: A multilingual analysis of individual human alignment with model attention
Human fixation patterns have been shown to correlate strongly with Transformer-based attention.
Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild
We argue that we need to evaluate model interpretability methods 'in the wild', i. e., in situations where professionals make critical decisions, and models can potentially assist them.
Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?
We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during task-reading as classical cognitive models of human attention.
How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns
Gender-neutral pronouns have recently been introduced in many languages to a) include non-binary people and b) as a generic singular.
Challenges and Strategies in Cross-Cultural NLP
Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages.
Balancing the composition of word embeddings across heterogenous data sets
Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications.
