201 citations · 1k across the 85 of their papers we have counts for
17 papers · 1 filter
PHD: Pixel-Based Language Modeling of Historical Documents
Nadav Borenstein, Phillip Rust, Desmond Elliott +1
The digitisation of historical documents has provided historians with unprecedented research opportunities. Yet, the conventional approach to analysing historical documents involve…
The Causal Influence of Grammatical Gender on Distributional Semantics
Karolina Stańczak, Kevin Du, Adina Williams +2
How much meaning influences gender assignment across languages is an active area of research in linguistics and cognitive science. We can view current approaches as aiming to deter…
Invisible Women in Digital Diplomacy: A Multidimensional Framework for Online Gender Bias Against Women Ambassadors Worldwide
Yevgeniy Golovchenko, Karolina Stańczak, Rebecca Adler-Nissen +2
Despite mounting evidence that women in foreign policy often bear the brunt of online hostility, the extent of online gender bias against diplomats remains unexplored. This paper o…
Social Bias Probing: Fairness Benchmarking for Language Models
Marta Marchiori Manerba, Karolina Stańczak, Riccardo Guidotti +1
While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limitin…
Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers
Yuxia Wang, Revanth Gangi Reddy, Zain Muhammad Mujahid +10
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. In this work, we…
People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
Indira Sen, Dennis Assenmacher, Mattia Samory +3
NLP models are used in a variety of critical social computing tasks, such as detecting sexist, racist, or otherwise hateful content. Therefore, it is imperative that these models a…
Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions
Lucie-Aimée Kaffee, Arnav Arora, Isabelle Augenstein
The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and the editors are encouraged to use the c…
Explaining Interactions Between Text Spans
Sagnik Ray Choudhury, Pepa Atanasova, Isabelle Augenstein
Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehensi…
Factuality Challenges in the Era of Large Language Models
Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha +15
The emergence of tools based on Large Language Models (LLMs), such as OpenAI's ChatGPT, Microsoft's Bing Chat, and Google's Bard, has garnered immense public attention. These incre…
Faithfulness Tests for Natural Language Explanations
Pepa Atanasova, Oana-Maria Camburu, Christina Lioma +3
Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as salie…
Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detection
Erik Arakelyan, Arnav Arora, Isabelle Augenstein
Stance Detection is concerned with identifying the attitudes expressed by an author towards a target of interest. This task spans a variety of domains ranging from social media opi…
Measuring Gender Bias in West Slavic Language Models
Sandra Martinková, Karolina Stańczak, Isabelle Augenstein
Pre-trained language models have been known to perpetuate biases from the underlying datasets to downstream tasks. However, these findings are predominantly based on monolingual la…
Measuring Intersectional Biases in Historical Documents
Nadav Borenstein, Karolina Stańczak, Thea Rolskov +3
Data-driven analyses of biases in historical texts can help illuminate the origin and development of biases prevailing in modern society. However, digitised historical documents po…
Multilingual Event Extraction from Historical Newspaper Adverts
Nadav Borenstein, Natalia da Silva Perez, Isabelle Augenstein
NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiri…
Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing
Lucie-Aimée Kaffee, Arnav Arora, Zeerak Talat +1
Dual use, the intentional, harmful reuse of technology and scientific artefacts, is a problem yet to be well-defined within the context of Natural Language Processing (NLP). Howeve…
TempEL: Linking Dynamically Evolving and Newly Emerging Entities
Klim Zaporojets, Lucie-Aimee Kaffee, Johannes Deleu +3
In our continuously evolving world, entities change over time and new, previously non-existing or unknown, entities appear. We study how this evolutionary scenario impacts the perf…
Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
Erik Arakelyan, Pasquale Minervini, Daniel Daza +2
Answering complex queries on incomplete knowledge graphs is a challenging task where a model needs to answer complex logical queries in the presence of missing knowledge. Prior wor…