Felix Hamborg
YOU?
Author Swipe
View article: Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning
Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning Open
Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performanc…
View article: How Negative Media Coverage Impacts Platform Governance: Evidence from Facebook, Twitter, and YouTube
How Negative Media Coverage Impacts Platform Governance: Evidence from Facebook, Twitter, and YouTube Open
Social media companies wield considerable power over what people can say and do online, with consequences for freedom of expression and participation in digital culture. Yet we still know little about the factors that shape these companies…
View article: Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition
Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition Open
Few-shot named entity recognition (NER) detects named entities within text using only a few annotated examples. One promising line of research is to leverage natural language descriptions of each entity type: the common label PER might, fo…
View article: Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs Open
Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current …
View article: What's in the News? Towards Identification of Bias by Commission, Omission, and Source Selection (COSS)
What's in the News? Towards Identification of Bias by Commission, Omission, and Source Selection (COSS) Open
In a world overwhelmed with news, determining which information comes from reliable sources or how neutral is the reported information in the news articles poses a challenge to news readers. In this paper, we propose a methodology for auto…
View article: Automated identification of bias inducing words in news articles using linguistic and context-oriented features
Automated identification of bias inducing words in news articles using linguistic and context-oriented features Open
Media has a substantial impact on public perception of events, and, accordingly, the way media presents events can potentially alter the beliefs and views of the public. One of the ways in which bias in news articles can be introduced is b…
View article: Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs Open
Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current …
View article: Revealing Media Bias in News Articles
Revealing Media Bias in News Articles Open
This open access book presents an interdisciplinary approach to automatically reveal biases in English news articles reporting on a given political event.
View article: Conclusion
Conclusion Open
This chapter concludes the doctoral thesis by summarizing the previously presented research (Sect. 7.1) and major contributions (Sect. 7.2). Lastly, the chapter discusses the limitations of the presented work and highlights ideas for futur…
View article: Media Bias Analysis
Media Bias Analysis Open
This chapter provides the first interdisciplinary literature review on media bias analysis, thereby contrasting manual and automated analysis approaches. Decade-long research in political science and other social sciences has resulted in c…
View article: Person-Oriented Framing Analysis
Person-Oriented Framing Analysis Open
This chapter proposes person-oriented framing analysis (PFA), our approach to reveal biases. In a discussion of the solution space to tackle media bias, the chapter uses the findings of the literature review from Chap. 2 to narrow the rese…
View article: Prototype
Prototype Open
This chapter demonstrates the effectiveness of person-oriented framing analysis (PFA) by implementing and evaluating a prototypical system for bias identification and communication. In the single-blind setting of the evaluation, only the P…
View article: Target Concept Analysis
Target Concept Analysis Open
This chapter details the first component of person-oriented framing analysis: target concept analysis. This component aims to find and resolve mentions of persons, which can be subject to media bias. The chapter introduces and discusses tw…
View article: Frame Analysis
Frame Analysis Open
This chapter details the last component of person-oriented framing analysis: frame analysis. The component aims to classify how persons are portrayed in news articles. The chapter introduces and discusses two approaches for this task. Firs…
View article: Introduction
Introduction Open
This chapter motivates and summarizes my research to reveal bias in news articles. Section 1.1 highlights the issues caused by slanted news coverage. The importance of these issues cannot be overestimated as systematically biased coverage …
View article: XCoref: Cross-document Coreference Resolution in the Wild
XCoref: Cross-document Coreference Resolution in the Wild Open
Datasets and methods for cross-document coreference resolution (CDCR) focus on events or entities with strict coreference relations. They lack, however, annotating and resolving coreference mentions with more abstract or loose relations th…
View article: Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort
Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort Open
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, …
View article: Do You Think It's Biased? How To Ask For The Perception Of Media Bias
Do You Think It's Biased? How To Ask For The Perception Of Media Bias Open
Media coverage possesses a substantial effect on the public perception of events. The way media frames events can significantly alter the beliefs and perceptions of our society. Nevertheless, nearly all media outlets are known to report ne…
View article: ANEA: Automated (Named) Entity Annotation for German Domain-Specific\n Texts
ANEA: Automated (Named) Entity Annotation for German Domain-Specific\n Texts Open
Named entity recognition (NER) is an important task that aims to resolve\nuniversal categories of named entities, e.g., persons, locations,\norganizations, and times. Despite its common and viable use in many use cases,\nNER is barely appl…
View article: How to Effectively Identify and Communicate Person-Targeting Media Bias in Daily News Consumption?
How to Effectively Identify and Communicate Person-Targeting Media Bias in Daily News Consumption? Open
Slanted news coverage strongly affects public opinion. This is especially true for coverage on politics and related issues, where studies have shown that bias in the news may influence elections and other collective decisions. Due to its v…
View article: How to Effectively Identify and Communicate Person-Targeting Media Bias\n in Daily News Consumption?
How to Effectively Identify and Communicate Person-Targeting Media Bias\n in Daily News Consumption? Open
Slanted news coverage strongly affects public opinion. This is especially\ntrue for coverage on politics and related issues, where studies have shown that\nbias in the news may influence elections and other collective decisions. Due to\nit…
View article: Newsalyze: Effective Communication of Person-Targeting Biases in News Articles
Newsalyze: Effective Communication of Person-Targeting Biases in News Articles Open
Media bias and its extreme form, fake news, can decisively affect public opinion. Especially when reporting on policy issues, slanted news coverage may strongly influence societal decisions, e.g., in democratic elections. Our paper makes t…
View article: Results and further resources concerning our pre-studies concerning revealing biases in news articles
Results and further resources concerning our pre-studies concerning revealing biases in news articles Open
Slanted news coverage strongly affects public opinion. This is especially true for coverage on politics and related issues, where studies have shown that bias in the news may strongly influence elections and other collective decisions. Due…
View article: Results and further resources concerning our pre-studies concerning revealing biases in news articles
Results and further resources concerning our pre-studies concerning revealing biases in news articles Open
Slanted news coverage strongly affects public opinion. This is especially true for coverage on politics and related issues, where studies have shown that bias in the news may strongly influence elections and other collective decisions. Due…
View article: Qualitative and Quantitative Analysis of Diversity in Cross-document Coreference Resolution Datasets.
Qualitative and Quantitative Analysis of Diversity in Cross-document Coreference Resolution Datasets. Open
Cross-document coreference resolution (CDCR) datasets, such as ECB+, contain manually annotated event-centric mentions of events and entities that form coreference chains with identity relations. ECB+ is a state-of-the-art CDCR dataset tha…
View article: Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes
Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes Open
Established cross-document coreference resolution (CDCR) datasets contain event-centric coreference chains of events and entities with identity relations. These datasets establish strict definitions of the coreference relations across rela…
View article: Do You Think It's Biased? How To Ask For The Perception Of Media Bias
Do You Think It's Biased? How To Ask For The Perception Of Media Bias Open
Media coverage possesses a substantial effect on the public perception of events. The way media frames events can significantly alter the beliefs and perceptions of our society. Nevertheless, nearly all media outlets are known to report ne…
View article: Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort
Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort Open
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality, …