Related papers: Objectifying the Subjective: Cognitive Biases in T…

An essential aspect of evaluating Large Language Models (LLMs) is identifying potential biases. This is especially relevant considering the substantial evidence that LLMs can replicate human social biases in their text outputs and further…

Argumentation is one of society's foundational pillars, and, sparked by advances in NLP and the vast availability of text data, automated mining of arguments receives increasing attention. A decisive property of arguments is their strength…

Topic models are widely used unsupervised models capable of learning topics - weighted lists of words and documents - from large collections of text documents. When topic models are used for discovery of topics in text collections, a…

Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts. Unfortunately, encoding experts' knowledge is often time consuming and expensive. We propose a…

Topic modelling is a text mining technique for identifying salient themes from a number of documents. The output is commonly a set of topics consisting of isolated tokens that often co-occur in such documents. Manual effort is often…

Human-in-the-loop topic modelling incorporates users' knowledge into the modelling process, enabling them to refine the model iteratively. Recent research has demonstrated the value of user feedback, but there are still issues to consider,…

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

Explainability is widely regarded as essential for trustworthy artificial intelligence systems. However, the metrics commonly used to evaluate counterfactual explanations are algorithmic evaluation metrics that are rarely validated against…

The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of…

Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for…

Coherence of text is an important attribute to be measured for both manually and automatically generated discourse; but well-defined quantitative metrics for it are still elusive. In this paper, we present a metric for scoring topical…

Understanding and modeling consumers' stylistic taste such as "sporty" is crucial for creating designs that truly connect with target audiences. However, capturing taste during the design process remains challenging because taste is…

Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization target. However,…

In code comprehension experiments, participants are usually told at the beginning what kind of code comprehension task to expect. Describing experiment scenarios and experimental tasks will influence participants in ways that are sometimes…

We improve the extraction of insights from customer reviews by restructuring the topic modelling pipeline to operate on opinion units - distinct statements that include relevant text excerpts and associated sentiment scores. Prior work has…

Assessing the quality of arguments and of the claims the arguments are composed of has become a key task in computational argumentation. However, even if different claims share the same stance on the same topic, their assessment depends on…

The convincingness of an argument does not only depend on its structure (logos), the person who makes the argument (ethos), but also on the emotion that it causes in the recipient (pathos). While the overall intensity and categorical values…

Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference…

We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic. Our approach enables users to (1) understand the semantic space of the model, (2)…

Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications.…