Bela Gipp

Bela Gipp
University of Göttingen | GAUG · Faculty of Mathematics and Computer Science

Prof. Dr. Ing.
Hiring new PhD candidates. Apply here: https://gipplab.org/hiring/

About

293
Publications
209,908
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,953
Citations
Additional affiliations
February 2015 - July 2018
University of Konstanz
Position
  • Juniorprofessor
Description
  • www.isg.uni-konstanz.de
August 2018 - March 2022
University of Wuppertal
Position
  • Professor (Full)
Description
  • http://www.gipp.com
April 2014 - January 2015
National Institute of Informatics
Position
  • PostDoc Position

Publications

Publications (293)
Book
Full-text available
Publication in the field of technical sciences Plagiarism is a problem with far-reaching consequences for the sciences. However, even today’s best software-based systems can only reliably identify copy&paste plagiarism. Disguised plagiarism forms, including paraphrased text, cross-language plagiarism, as well as structural and idea plagiarism often...
Article
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 understanding of the task, and aligns proposed techniqu...
Preprint
Full-text available
Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task. This study addresses the challenge of automated collecting test datase...
Preprint
Full-text available
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 language models (LLMs), which have the benefit of bett...
Preprint
Full-text available
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 quality. LLMs have shown promising results in annotating...
Preprint
Full-text available
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 supplementary resources (e.g., presentation slides...
Article
Full-text available
User experience (UX) is a part of human–computer interaction research and focuses on increasing intuitiveness, transparency, simplicity, and trust for the system users. Most UX research for machine learning or natural language processing (NLP) focuses on a data-driven methodology. It engages domain users mainly for usability evaluation. Moreover, m...
Preprint
Full-text available
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 relevance and avoid hallucination. We introduce a...
Conference Paper
Full-text available
Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopt...
Preprint
Full-text available
We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such as author names, titles, publication dates, and keywords, to create standardized annotations within the document. CiteAssist automatically attaches the BibTeX citation t...
Preprint
Full-text available
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 paraphrases into different linguistic changes and offe...
Preprint
Full-text available
Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study systematically and empirically evaluates which linguistic features influence models through paraphrase types, i.e., di...
Preprint
Full-text available
Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although reviews have been conducted on this topic, there is a lack of comprehensive work detailing the challenges of dialogue summarization, unifying the differing understanding of the task, and aligning proposed techniques, datasets,...
Preprint
Full-text available
Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation i...
Chapter
Full-text available
Plagiarism is a pressing concern, even more so with the availability of large language models. Existing plagiarism detection systems reliably find copied and moderately reworded text but fail for idea plagiarism, especially in mathematical science, which heavily uses formal mathematical notation. We make two contributions. First, we establish a tax...
Preprint
Full-text available
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, the first large-scale multi-task pre-training approach explicitly tailored for media bias detection. To enable pre-training at scale, we...
Article
Full-text available
Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula no...
Preprint
Full-text available
We present »PhysWikiQuiz«, a physics question generation and test engine. Our system, hosted by Wikimedia, utilizes Wikidata, an open, community-managed database, to acquire physics knowledge. For the teacher's input of a given concept name, it produces personalized questions for each individual student. Subsequently, it uses a Computer Algebra Sys...
Preprint
Full-text available
User experience (UX) is a part of human-computer interaction (HCI) research and focuses on increasing intuitiveness, transparency, simplicity, and trust for system users. Most of the UX research for machine learning (ML) or natural language processing (NLP) focuses on a data-driven methodology, i.e., it fails to focus on users' requirements, and en...
Chapter
In scientific publications, citations allow readers to assess the authenticity of the presented information and verify it in the original context. News articles, however, for various reasons do not contain citations and only rarely refer readers to further sources. As a result, readers often cannot assess the authenticity of the presented informati...
Preprint
Full-text available
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 symbols, while their translation requires extreme preci...
Preprint
Full-text available
This demo paper presents the first tool to annotate the reuse of text, images, and mathematical formulae in a document pair-TEIMMA. Annotating content reuse is particularly useful to develop plagiarism detection algorithms. Real-world content reuse is often obfuscated, which makes it challenging to identify such cases. TEIMMA allows entering the ob...
Preprint
Full-text available
This project investigated new approaches and technologies to enhance the accessibility of mathematical content and its semantic information for a broad range of information retrieval applications. To achieve this goal, the project addressed three main research challenges: (1) syntactic analysis of mathematical expressions, (2) semantic enrichment o...
Preprint
Full-text available
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 automatically identifying bias by commission, omission, and source selection (COSS) as a joint threefold objective,...
Preprint
Full-text available
It allows any two parties that are either both on the same network or connected via the internet to transfer the contents of a file based on a particular sequence of words. Peer discovery happens via multicast DNS if both peers are on the same network or via entries in the distributed hash table (DHT) of the InterPlanetary File-System (IPFS) if bot...
Preprint
Full-text available
Although media bias detection is a complex multi-task problem, there is, to date, no unified benchmark grouping these evaluation tasks. We introduce the Media Bias Identification Benchmark (MBIB), a comprehensive benchmark that groups different types of media bias (e.g., linguistic, cognitive, political) under a common framework to test how prospec...
Preprint
Full-text available
The growing prominence of large language models, such as GPT-4 and ChatGPT, has led to increased concerns over academic integrity due to the potential for machine-generated content and paraphrasing. Although studies have explored the detection of human- and machine-paraphrased content, the comparison between these types of content remains underexpl...
Preprint
Full-text available
Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are available, but recent performance benchmarks are rare. Moreover, such benchmarks typically cover only a few conte...
Chapter
Full-text available
Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are available, but recent performance benchmarks are rare. Moreover, such benchmarks typically cover only a few conte...
Preprint
Full-text available
Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula no...
Preprint
Full-text available
This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives. The dedicated interfaces allow its users to identify trends in research activity , accessibility, author’s productivity, venues, statistics, topics of interest, and the impact of computer science research...
Article
Full-text available
Centralized networks inevitably exhibit single points of failure that malicious actors regularly target. Decentralized networks are more resilient if numerous participants contribute to the network’s functionality. Most decentralized networks employ incentive mechanisms to coordinate the participation and cooperation of peers and thereby ensure the...
Preprint
Full-text available
The increasing number of questions on Question Answering (QA) platforms like Math Stack Exchange (MSE) signifies a growing information need to answer math-related questions. However, there is currently very little research on approaches for an open data QA system that retrieves mathematical formulae using their concept names or querying formula ide...
Preprint
Full-text available
Small to medium-scale data science experiments often rely on research software developed ad-hoc by individual scientists or small teams. Often there is no time to make the research software fast, reusable, and open access. The consequence is twofold. First, subsequent researchers must spend significant work hours building upon the proposed hypothes...
Preprint
Full-text available
Media has a substantial impact on the public perception of events. A one-sided or polarizing perspective on any topic is usually described as media bias. One of the ways how bias in news articles can be introduced is by altering word choice. Biased word choices are not always obvious, nor do they exhibit high context-dependency. Hence, detecting bi...
Chapter
Full-text available
Eine Einführung in die rechtlichen, methodischen und technologischen Probleme und Lösungen für die Prävention und Erkennung wissenschaftlicher Plagiate
Preprint
Full-text available
Despite the recent success of multi-task learning and pre-finetuning for natural language understanding, few works have studied the effects of task families on abstractive text summarization. Task families are a form of task grouping during the pre-finetuning stage to learn common skills, such as reading comprehension. To close this gap, we analyze...
Preprint
Full-text available
Since the COVID-19 outbreak, the use of digital learning or education platforms has significantly increased. Teachers now digitally distribute homework and provide exercise questions. In both cases, teachers need to continuously develop novel and individual questions. This process can be very time-consuming and should be facilitated and accelerated...
Preprint
Full-text available
This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives. The dedicated interfaces allow its users to identify trends in research activity, productivity, accessibility, author's productivity, venues' statistics, topics of interest, and the impact of computer sci...
Preprint
Full-text available
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 transformers in generating machine-paraphrased plagiarism and their detection is still developing in the litera...
Preprint
Full-text available
Recent years have witnessed growing consolidation of web operations. For example, the majority of web traffic now originates from a few organizations, and even micro-websites often choose to host on large pre-existing cloud infrastructures. In response to this, the "Decentralized Web" attempts to distribute ownership and operation of web services m...
Article
Full-text available
Wikipedia combines the power of AI solutions and human reviewers to safeguard article quality. Quality control objectives include detecting malicious edits, fixing typos, and spotting inconsistent formatting. However, no automated quality control mechanisms currently exist for mathematical formulae. Spell checkers are widely used to highlight textu...
Conference Paper
Full-text available
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 related tests but typically ignore anaphora with more vague context-dependent loose coreference relations. In this...
Conference Paper
Full-text available
Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due...
Preprint
Full-text available
Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due...
Preprint
Full-text available
DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent metadata (e.g., abstracts, author affiliations, citations) from the publication texts to create the DBLP Discov...