565 citations · 1k across the 46 of their papers we have counts for
47 papers
Citance-Contextualized Summarization of Scientific Papers
Shahbaz Syed, Ahmad Dawar Hakimi, Khalid Al-Khatib +1
Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relation…
Indicative Summarization of Long Discussions
Shahbaz Syed, Dominik Schwabe, Khalid Al-Khatib +1
Online forums encourage the exchange and discussion of different stances on many topics. Not only do they provide an opportunity to present one's own arguments, but may also gather…
Evaluating Generative Ad Hoc Information Retrieval
Lukas Gienapp, Harrisen Scells, Niklas Deckers +9
Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval system…
Commercialized Generative AI: A Critical Study of the Feasibility and Ethics of Generating Native Advertising Using Large Language Models in Conversational Web Search
Ines Zelch, Matthias Hagen, Martin Potthast
How will generative AI pay for itself? Unless charging users for access, selling advertising is the only alternative. Especially in the multi-billion dollar web search market with…
Generating Natural Language Queries for More Effective Systematic Review Screening Prioritisation
Shuai Wang, Harrisen Scells, Martin Potthast +2
Screening prioritisation in medical systematic reviews aims to rank the set of documents retrieved by complex Boolean queries. Prioritising the most important documents ensures tha…
OpinionConv: Conversational Product Search with Grounded Opinions
Vahid Sadiri Javadi, Martin Potthast, Lucie Flek
When searching for products, the opinions of others play an important role in making informed decisions. Subjective experiences about a product can be a valuable source of informat…
Manipulating Embeddings of Stable Diffusion Prompts
Niklas Deckers, Julia Peters, Martin Potthast
Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuo…
GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration
Aleksandra Piktus, Odunayo Ogundepo, Christopher Akiki +6
Noticing the urgent need to provide tools for fast and user-friendly qualitative analysis of large-scale textual corpora of the modern NLP, we propose to turn to the mature and wel…
The Information Retrieval Experiment Platform
Maik Fröbe, Jan Heinrich Reimer, Sean MacAvaney +6
We integrate ir_datasets, ir_measures, and PyTerrier with TIRA in the Information Retrieval Experiment Platform (TIREx) to promote more standardized, reproducible, scalable, and ev…
Modeling Appropriate Language in Argumentation
Timon Ziegenbein, Shahbaz Syed, Felix Lange +2
Online discussion moderators must make ad-hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existi…
Using Language Models on Low-end Hardware
Fabian Ziegner, Janos Borst, Andreas Niekler +1
This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture…
Perspectives on Large Language Models for Relevance Judgment
Guglielmo Faggioli, Laura Dietz, Charles Clarke +8
When asked, large language models (LLMs) like ChatGPT claim that they can assist with relevance judgments but it is not clear whether automated judgments can reliably be used in ev…
The Archive Query Log: Mining Millions of Search Result Pages of Hundreds of Search Engines from 25 Years of Web Archives
Jan Heinrich Reimer, Sebastian Schmidt, Maik Fröbe +5
The Archive Query Log (AQL) is a previously unused, comprehensive query log collected at the Internet Archive over the last 25 years. Its first version includes 356 million queries…
Paraphrase Acquisition from Image Captions
Marcel Gohsen, Matthias Hagen, Martin Potthast +1
We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same "message") and to create and analyze a corresponding…
Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face
Christopher Akiki, Odunayo Ogundepo, Aleksandra Piktus +4
We present Spacerini, a tool that integrates the Pyserini toolkit for reproducible information retrieval research with Hugging Face to enable the seamless construction and deployme…
Topic Ontologies for Arguments
Yamen Ajjour, Johannes Kiesel, Benno Stein +1
Many computational argumentation tasks, like stance classification, are topic-dependent: the effectiveness of approaches to these tasks significantly depends on whether the approac…
The Infinite Index: Information Retrieval on Generative Text-To-Image Models
Niklas Deckers, Maik Fröbe, Johannes Kiesel +4
Conditional generative models such as DALL-E and Stable Diffusion generate images based on a user-defined text, the prompt. Finding and refining prompts that produce a desired imag…
SMAuC -- The Scientific Multi-Authorship Corpus
Janek Bevendorff, Philipp Sauer, Lukas Gienapp +4
The rapidly growing volume of scientific publications offers an interesting challenge for research on methods for analyzing the authorship of documents with one or more authors. Ho…
Summary Workbench: Unifying Application and Evaluation of Text Summarization Models
Shahbaz Syed, Dominik Schwabe, Martin Potthast
This paper presents Summary Workbench, a new tool for developing and evaluating text summarization models. New models and evaluation measures can be easily integrated as Docker-bas…
Differential Bias: On the Perceptibility of Stance Imbalance in Argumentation
Alonso Palomino, Martin Potthast, Khalid Al-Khatib +1
Most research on natural language processing treats bias as an absolute concept: Based on a (probably complex) algorithmic analysis, a sentence, an article, or a text is classified…
WARC-DL: Scalable Web Archive Processing for Deep Learning
Niklas Deckers, Martin Potthast
Web archives have grown to petabytes. In addition to providing invaluable background knowledge on many social and cultural developments over the last 30 years, they also provide va…
Trigger Warnings: Bootstrapping a Violence Detector for FanFiction
Magdalena Wolska, Christopher Schröder, Ole Borchardt +2
We present the first dataset and evaluation results on a newly defined computational task of trigger warning assignment. Labeled corpus data has been compiled from narrative works…
Sparse Pairwise Re-ranking with Pre-trained Transformers
Lukas Gienapp, Maik Fröbe, Matthias Hagen +1
Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than po…
How Train-Test Leakage Affects Zero-shot Retrieval
Maik Fröbe, Christopher Akiki, Martin Potthast +1
Neural retrieval models are often trained on (subsets of) the millions of queries of the MS MARCO / ORCAS datasets and then tested on the 250 Robust04 queries or other TREC benchma…