AIConfPaper
← Search

Bela Gipp

22 accepted papers

2025

BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages

Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif +42
ACL 2025long

People worldwide use language in subtle and complex ways to express emotions. Although emotion recognition–an umbrella term for several NLP tasks–impacts various applications within NLP and beyond, most work in this area has focused on high-resource languages. This has led to significant disparities…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization (Abstract Reprint)

Frederic Kirstein, Jan Philip Wahle, Bela Gipp, Terry Ruas
IJCAI 2025

Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although focused reviews have been conducted on this topic, there is a lack of comprehensive work that details the core challenges of dialogue summarization, unifies the differing under

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields

Jan Philip Wahle, Terry Lima Ruas, Mohamed Abdalla, Bela Gipp, Saif M. Mohammad
COLING 2025main

This study examines the tendency to cite older work across 20 fields of study over 43 years (1980–2023). We put NLP’s propensity to cite older work in the context of these 20 other fields to analyze whether NLP shows similar temporal citation patterns to them over time or whether differences can be…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator

Frederic Thomas Kirstein, Terry Lima Ruas, Bela Gipp
COLING 2025industry

The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors. Recent studies suggest using large lang…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions

Frederic Kirstein, Sonu Kumar, Terry Ruas, Bela Gipp
EMNLP 2025

Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes t

Cited by 0Source ↗PDF ↗Scholar ↗
2025

The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection

Tomáš Horych, Christoph Mandl, Terry Ruas, Andre Greiner-Petter, Bela Gipp, Akiko Aizawa +1
NAACL 2025findings

High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data qualit…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2025

Towards Human Understanding of Paraphrase Types in Large Language Models

Dominik Meier, Jan Philip Wahle, Terry Lima Ruas, Bela Gipp
COLING 2025main

Paraphrases represent a human’s intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpretability of specific text changes. Atomic paraphrase types (APT) decompose para…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Voting or Consensus? Decision-Making in Multi-Agent Debate

Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, Bela Gipp
ACL 2025finding

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic comparison of decision protocols is difficult because many studies al…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

What’s Wrong? Refining Meeting Summaries with LLM Feedback

Frederic Thomas Kirstein, Terry Lima Ruas, Bela Gipp
COLING 2025main

Meeting summarization has become a critical task since digital encounters have become a common practice. Large language models (LLMs) show great potential in summarization, offering enhanced coherence and context understanding compared to traditional methods. However, they still struggle to maintain…

Cited by 7Source ↗PDF ↗Scholar ↗
2025

You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations

Frederic Kirstein, Muneeb Khan, Jan Philip Wahle, Terry Ruas, Bela Gipp
ACL 2025finding

Meeting summarization suffers from limited high-quality data, mainly due to privacy restrictions and expensive collection processes. We address this gap with FAME, a dataset of 500 meetings in English and 300 in German produced by MIMIC, our new multi-agent meeting synthesis framework that generates…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

MAGPIE: Multi-Task Analysis of Media-Bias Generalization with Pre-Trained Identification of Expressions

Tomáš Horych, Martin Paul Wessel, Jan Philip Wahle, Terry Ruas, Jerome Waßmuth, André Greiner-Petter +3
COLING 2024main

Media bias detection poses a complex, multifaceted problem traditionally tackled using single-task models and small in-domain datasets, consequently lacking generalizability. To address this, we introduce MAGPIE, a large-scale multi-task pre-training approach explicitly tailored for media bias detec…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization

Frederic Kirstein, Terry Ruas, Robert Kratel, Bela Gipp
EMNLP 2024industry

Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings’ content.Previous attempts to address these issues by considering related s…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

What’s under the hood: Investigating Automatic Metrics on Meeting Summarization

Frederic Kirstein, Jan Philip Wahle, Terry Ruas, Bela Gipp
EMNLP 2024finding

Meeting summarization has become a critical task considering the increase in online interactions. Despite new techniques being proposed regularly, the evaluation of meeting summarization techniques relies on metrics not tailored to capture meeting-specific errors, leading to ineffective assessment.…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

Neural Machine Translation for Mathematical Formulae

Felix Petersen, Moritz Schubotz, Andre Greiner-Petter, Bela Gipp
ACL 2023long

We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine translation on natural language, mathematical formulae have a much smaller vocabulary and much longer sequences of symbo…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields

Jan Philip Wahle, Terry Ruas, Mohamed Abdalla, Bela Gipp, Saif M. Mohammad
EMNLP 2023long main

Natural Language Processing (NLP) is poised to substantially influence the world. However, significant progress comes hand-in-hand with substantial risks. Addressing them requires broad engagement with various fields of study. Yet, little empirical work examines the state of such engagement (past or…

Cited by 0Source ↗code ↗Scholar ↗
2022

How Large Language Models are Transforming Machine-Paraphrase Plagiarism

Jan Philip Wahle, Terry Ruas, Frederic Kirstein, Bela Gipp
EMNLP 2022main

The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work.However, the role of large autoregressive models in generating machine-paraphrased plagiarism and their…

Cited by 63Source ↗PDF ↗Scholar ↗
2022

Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings

Malte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp, Georg Rehm
EMNLP 2022main

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. Prior work relies on discrete citation relations to generate c…

Cited by 89Source ↗PDF ↗code ↗Scholar ↗
2021

Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts

Timo Spinde, Manuel Plank, Jan-David Krieger, Terry Ruas, Bela Gipp, Akiko Aizawa
EMNLP 2021finding

Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of a gold standard dat…

Cited by 84Source ↗PDF ↗code ↗Scholar ↗
2020

Aspect-based Document Similarity for Research Papers

Malte Ostendorff, Terry Ruas, Till Blume, Bela Gipp, Georg Rehm
COLING 2020main

Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of applications like recommender systems that rely on document similarity. In…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗