Related papers: Underspecified Scientific Claims in Nanopublicatio…
This paper presents the results of research on supervised extractive text summarisation for scientific articles. We show that a simple sequential tagging model based only on the text within a document achieves high results against a simple…
Evidence plays a crucial role in any biomedical research narrative, providing justification for some claims and refutation for others. We seek to build models of scientific argument using information extraction methods from full-text…
Providing visual summaries of scientific publications can increase information access for readers and thereby help deal with the exponential growth in the number of scientific publications. Nonetheless, efforts in providing visual…
The number of scientific articles has grown rapidly over the years and there are no signs that this growth will slow down in the near future. Because of this, it becomes increasingly difficult to keep up with the latest developments in a…
Numerous studies have revealed biases within the scientific communication system and across all scientific fields. For example, already prominent researchers receive disproportional credit compared to their (almost) equally qualified…
This paper is under review in AI and Ethics This study examines whether large language models (LLMs) can reliably answer scientific questions and demonstrates how easily they can be influenced by fringe scientific material. The authors…
Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications. Nevertheless, how to efficiently evaluate such word embeddings in the informal domain such as Twitter or forums, remains an…
Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits reproducibility and…
Large language models (LLMs) have grown in their usage to provide support for question answering across numerous disciplines. The models on their own have already shown promise for answering basic questions, however fail quickly where…
Mechanistic interpretability papers increasingly use causal vocabulary: circuits, mediators, causal abstraction, monosemanticity. Such claims require explicit identification assumptions. A purposive audit of 10 papers across four…
Selecting the best scientific venue (i.e., conference/journal) for the submission of a research article constitutes a multifaceted challenge. Important aspects to consider are the suitability of research topics, a venue's prestige, and the…
Visual representations are becoming important in science communication and education. This explorative study investigates the perception of STEM researchers, without any specific visual design background, and the value of visual…
An important way for describing groups is by finite presentations. Large presentations arise in practice which are poorly suited for either human or computer use. Presentation simplification processes which take bad presentations and…
This paper presents novel prompting techniques to improve the performance of automatic summarization systems for scientific articles. Scientific article summarization is highly challenging due to the length and complexity of these…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
Considerable scientific work involves locating, analyzing, systematizing, and synthesizing other publications. Its results end up in a paper's "background" section or in standalone articles, which include meta-analyses and systematic…
In this position paper we present a new approach for discovering some special classes of assertional knowledge in the text by using large RDF repositories, resulting in the extraction of new non-taxonomic ontological relations. Also we use…
The web does not only enable new forms of science, it also creates new possibilities to study science and new digital scholarship. This paper brings together multiple perspectives: from individual researchers seeking the best options to…
Proper field delineation plays an important role in scientometric studies, although it is a tough task. Based on an emerging and interdisciplinary field, nanoscience and nanotechnology, this paper highlights the problem of field…
One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges…