Search Results for author:
Found 78 papers, 51 papers with code
Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
Stay Focused: Problem Drift in Multi-Agent Debate
To identify the reasons for this issue, we perform a human study with eight experts on discussions suffering from problem drift, who find the most common issues are a lack of progress (35% of cases), low-quality feedback (26% of cases), and a lack of clarity (25% of cases).
Voting or Consensus? Decision-Making in Multi-Agent Debate
Our results show that voting protocols improve performance by 13. 2% in reasoning tasks and consensus protocols by 2. 8% in knowledge tasks over the other decision protocol.
You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with a Multi-Agent Conversations
Meeting summarization suffers from limited high-quality data, mainly due to privacy restrictions and expensive collection processes.
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
In this paper, we present BRIGHTER-- a collection of multilabeled emotion-annotated datasets in 28 different languages.
Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain knowledge and training for the annotation task.
Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator
The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically.
The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection
Our classifier, fine-tuned on this dataset, surpasses all of the annotator LLMs by 5-9 percent in Matthews Correlation Coefficient (MCC) and performs close to or outperforms the model trained on human-labeled data when evaluated on two media bias benchmark datasets (BABE and BASIL).
Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
Previous attempts to address these issues by considering related supplementary resources (e. g., presentation slides) alongside transcripts are hindered by models' limited context sizes and handling the additional complexities of the multi-source tasks, such as identifying relevant information in additional files and seamlessly aligning it with the meeting content.
What's Wrong? Refining Meeting Summaries with LLM Feedback
Meeting summarization has become a critical task since digital encounters have become a common practice.
CiteAssist: A System for Automated Preprint Citation and BibTeX Generation
We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation.
Towards Human Understanding of Paraphrase Types in ChatGPT
The dataset also provides a human preference ranking of paraphrases with different types that can be used to fine-tune models with RLHF and DPO methods.
Paraphrase Types Elicit Prompt Engineering Capabilities
In particular, changes in morphology and lexicon, i. e., the vocabulary used, showed promise in improving prompts.
CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization
Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries.
Abstractive Dialogue Summarization
Abstractive Text Summarization
+1
Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges
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.
What's under the hood: Investigating Automatic Metrics on Meeting Summarization
Meeting summarization has become a critical task considering the increase in online interactions.
Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange
In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions.
MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions
MAGPIE confirms that MTL is a promising approach for addressing media bias detection, enhancing the accuracy and efficiency of existing models.
Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields
This study examines the tendency to cite older work across 20 fields of study over 43 years (1980--2023).
Text-Guided Image Clustering
We, therefore, propose Text-Guided Image Clustering, i. e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text.
Taxonomy of Mathematical Plagiarism
Second, we analyze the best-performing approaches to detect plagiarism and mathematical content similarity on the newly established taxonomy.
The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias
However, we have identified a lack of interdisciplinarity in existing projects, and a need for more awareness of the various types of media bias to support methodologically thorough performance evaluations of media bias detection systems.
We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields
We analyzed ~77k NLP papers, ~3. 1m citations from NLP papers to other papers, and ~1. 8m citations from other papers to NLP papers.
Paraphrase Types for Generation and Detection
Current approaches in paraphrase generation and detection heavily rely on a single general similarity score, ignoring the intricate linguistic properties of language.
Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications
Generative UX research employs domain users at the initial stages of prototype development, i. e., ideation and concept evaluation, and the last stage for evaluating system usefulness and user utility.
Neural Machine Translation for Mathematical Formulae
We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages.
TEIMMA: The First Content Reuse Annotator for Text, Images, and Math
This demo paper presents the first tool to annotate the reuse of text, images, and mathematical formulae in a document pair -- TEIMMA.
Methods and Tools to Advance the Retrieval of Mathematical Knowledge from Digital Libraries for Search-, Recommendation-, and Assistance-Systems
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.
Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection
A unified benchmark encourages the development of more robust systems and shifts the current paradigm in media bias detection evaluation towards solutions that tackle not one but multiple media bias types simultaneously.
Paraphrase Detection: Human vs. Machine Content
Additionally, we identify four datasets as the most diverse and challenging for paraphrase detection.
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents
Using the new framework, we benchmark ten freely available tools in extracting document metadata, bibliographic references, tables, and other content elements from academic PDF documents.
Discovery and Recognition of Formula Concepts using Machine Learning
Our long-term goal is to generalize citation-based IR methods and apply this generalized method to both classical references and mathematical concepts.
Collaborative and AI-aided Exam Question Generation using Wikidata in Education
To address this need, we propose a multilingual Wikimedia framework that allows for collaborative worldwide teacher knowledge engineering and subsequent AI-aided question generation, test, and correction.
Mining Mathematical Documents for Question Answering via Unsupervised Formula Labeling
In this paper, we aim to bridge the gap by presenting data mining methods and benchmark results to employ Mathematical Entity Linking (MathEL) and Unsupervised Formula Labeling (UFL) for semantic formula search and mathematical question answering (MathQA) on the arXiv preprint repository, Wikipedia, and Wikidata, which is part of the Wikimedia ecosystem of free knowledge.
Caching and Reproducibility: Making Data Science experiments faster and FAIRer
In that case, the overall effort to iteratively improve the software and rerun the experiments creates significant time pressure on the researchers.
Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles
Media has a substantial impact on the public perception of events.
Analyzing Multi-Task Learning for Abstractive Text Summarization
Further, we find that choice and combinations of task families influence downstream performance more than the training scheme, supporting the use of task families for abstractive text summarization.
CS-Insights: A System for Analyzing Computer Science Research
This paper presents CS-Insights, an interactive web application to analyze computer science publications from DBLP through multiple perspectives.
How Large Language Models are Transforming Machine-Paraphrased Plagiarism
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.
Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
A Domain-adaptive Pre-training Approach for Language Bias Detection in News
We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0. 814.
D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research
We present an initial analysis focused on the volume of computer science research (e. g., number of papers, authors, research activity), trends in topics of interest, and citation patterns.
Specialized Document Embeddings for Aspect-based Similarity of Research Papers
We compare and analyze three generic document embeddings, six specialized document embeddings and a pairwise classification baseline in the context of research paper recommendations.
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings
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.
Ranked #1 on
Document Classification
on SciDocs (MeSH)
Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort
Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques.
Do You Think It's Biased? How To Ask For The Perception Of Media Bias
To name an example: Intending to measure bias in a news article, should we ask, "How biased is the article?"
Towards A Reliable Ground-Truth For Biased Language Detection
Our results demonstrate the existing crowdsourcing approaches' lack of data quality, underlining the need for a trained expert framework to gather a more reliable dataset.
TASSY -- A Text Annotation Survey System
We present a free and open-source tool for creating web-based surveys that include text annotation tasks.
Identification of Biased Terms in News Articles by Comparison of Outlet-specific Word Embeddings
The underlying idea is that the context of biased words in different news outlets varies more strongly than the one of non-biased words, since the perception of a word as being biased differs depending on its context.
ANEA: Automated (Named) Entity Annotation for German Domain-Specific Texts
Named entity recognition (NER) is an important task that aims to resolve universal categories of named entities, e. g., persons, locations, organizations, and times.
Detecting Cross-Language Plagiarism using Open Knowledge Graphs
Identifying cross-language plagiarism is challenging, especially for distant language pairs and sense-for-sense translations.
Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection
We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.
How to Effectively Identify and Communicate Person-Targeting Media Bias in Daily News Consumption?
We present an in-progress system for news recommendation that is the first to automate the manual procedure of content analysis to reveal person-targeting biases in news articles reporting on policy issues.
Newsalyze: Effective Communication of Person-Targeting Biases in News Articles
Our study further suggests that our content-driven identification method detects groups of similarly slanted news articles due to substantial biases present in individual news articles.
A Qualitative Evaluation of User Preference for Link-based vs. Text-based Recommendations of Wikipedia Articles
We conclude that users of literature recommendation systems can benefit most from hybrid approaches that combine both link- and text-based approaches, where the user's information needs and preferences should control the weighting for the approaches used.
Towards Evaluation of Cross-document Coreference Resolution Models Using Datasets with Diverse Annotation Schemes
In this paper, we qualitatively and quantitatively compare the annotation schemes of ECB+, a CDCR dataset with identity coreference relations, and NewsWCL50, a CDCR dataset with a mix of loose context-dependent and strict coreference relations.
coreference-resolution
Cross Document Coreference Resolution
+1
XCoref: Cross-document Coreference Resolution in the Wild
Bridging and loose coreference relations trigger associations that may lead to exposing news readers to bias by word choice and labeling.
coreference-resolution
Cross Document Coreference Resolution
Towards Explaining STEM Document Classification using Mathematical Entity Linking
The results indicate that mathematical entities have the potential to provide high explainability as they are a crucial part of a STEM document.
Concept Identification of Directly and Indirectly Related Mentions Referring to Groups of Persons
Specifically, the approach clusters mentions of groups of persons that act as non-named entity actors in the texts, e. g., "migrant families" = "asylum-seekers."
Incorporating Word Sense Disambiguation in Neural Language Models
We present two supervised (pre-)training methods to incorporate gloss definitions from lexical resources into neural language models (LMs).
Towards Target-dependent Sentiment Classification in News Articles
Extensive research on target-dependent sentiment classification (TSC) has led to strong classification performances in domains where authors tend to explicitly express sentiment about specific entities or topics, such as in reviews or on social media.
Evaluating Document Representations for Content-based Legal Literature Recommendations
Simultaneously, legal recommender systems are typically evaluated in small-scale user study without any public available benchmark datasets.
Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection
The rise of language models such as BERT allows for high-quality text paraphrasing.
Identifying Machine-Paraphrased Plagiarism
Employing paraphrasing tools to conceal plagiarized text is a severe threat to academic integrity.
Aspect-based Document Similarity for Research Papers
Our findings motivate future research of aspect-based document similarity and the development of a recommender system based on the evaluated techniques.
AutoMSC: Automatic Assignment of Mathematics Subject Classification Labels
Moreover, we find that the method's confidence score allows for reducing the effort by 86% compared to the manual coarse-grained classification effort while maintaining a precision of 81% for automatically classified articles.
A First Step Towards Content Protecting Plagiarism Detection
Plagiarism detection systems are essential tools for safeguarding academic and educational integrity.
Classification and Clustering of arXiv Documents, Sections, and Abstracts, Comparing Encodings of Natural and Mathematical Language
In this paper, we show how selecting and combining encodings of natural and mathematical language affect classification and clustering of documents with mathematical content.
Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles
In this paper, we model the problem of finding the relationship between two documents as a pairwise document classification task.
Mathematical Formulae in Wikimedia Projects 2020
This poster summarizes our contributions to Wikimedia's processing pipeline for mathematical formulae.
Discovering Mathematical Objects of Interest -- A Study of Mathematical Notations
The contributions of our presented research are as follows: (1) we present the first distributional analysis of mathematical formulae on arXiv and zbMATH; (2) we retrieve relevant mathematical objects for given textual search queries (e. g., linking $P_{n}^{(\alpha, \beta)}\!\left(x\right)$ with `Jacobi polynomial'); (3) we extend zbMATH's search engine by providing relevant mathematical formulae; and (4) we exemplify the applicability of the results by presenting auto-completion for math inputs as the first contribution to math recommendation systems.
NewsDeps: Visualizing the Origin of Information in News Articles
In scientific publications, citations allow readers to assess the authenticity of the presented information and verify it in the original context.
Enriching BERT with Knowledge Graph Embeddings for Document Classification
In this paper, we focus on the classification of books using short descriptive texts (cover blurbs) and additional metadata.
Giveme5W1H: A Universal System for Extracting Main Events from News Articles
Event extraction from news articles is a commonly required prerequisite for various tasks, such as article summarization, article clustering, and news aggregation.
Introducing MathQA -- A Math-Aware Question Answering System
This formulae originate from the knowledge-base Wikidata.
Improving Academic Plagiarism Detection for STEM Documents by Analyzing Mathematical Content and Citations
Overall, we show that analyzing the similarity of mathematical content and academic citations is a striking supplement for conventional text-based detection approaches for academic literature in the STEM disciplines.
Why Machines Cannot Learn Mathematics, Yet
Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods.
Towards Formula Translation using Recursive Neural Networks
We implemented the first translator for mathematical formulae based on recursive neural networks.
