A5014534985- Topic Modeling
- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Information Retrieval and Search Behavior
- Web Data Mining and Analysis
- Speech and dialogue systems
- Mobile Crowdsensing and Crowdsourcing
- Advanced Text Analysis Techniques
- Misinformation and Its Impacts
- Text and Document Classification Technologies
- Data Quality and Management
- Data Management and Algorithms
- Educational Games and Gamification
- Recommender Systems and Techniques
- Expert finding and Q&A systems
- Digital Games and Media
- Hate Speech and Cyberbullying Detection
- Spam and Phishing Detection
- Augmented Reality Applications
- Sentiment Analysis and Opinion Mining
- Data Visualization and Analytics
- Image Retrieval and Classification Techniques
- Complex Network Analysis Techniques
- Advanced Database Systems and Queries
- Wikis in Education and Collaboration
University of Regensburg
2019-2024
Bar-Ilan University
2021
University of Helsinki
2021
Tel Aviv University
2021
Technical University of Darmstadt
2021
University of Copenhagen
2021
Edinburgh Napier University
2021
Universitat Pompeu Fabra
2021
University of Amsterdam
2021
University of Antwerp
2021
This report documents the program and outcomes of Dagstuhl Seminar 23031 "Frontiers Information Access Experimentation for Research Education", which brought together 38 participants from 12 countries. The seminar addressed technology-enhanced information access (information retrieval, recommender systems, natural language processing) specifically focused on developing more responsible experimental practices leading to valid results, both research as well scientific education. featured a...
We are witnessing a paradigm shift in Human Language Technology (HLT) that may well have an impact on the field comparable to statistical revolution: acquiring large-scale resources by exploiting collective intelligence. An illustration of this new approach is Phrase Detectives , interactive online game with purpose for creating anaphorically annotated makes use highly distributed population contributors different levels expertise. The article first all give overview aspects Detectives, from...
The analysis of crowdsourced annotations in natural language processing is concerned with identifying (1) gold standard labels, (2) annotator accuracies and biases, (3) item difficulties error patterns. Traditionally, majority voting was used for 1, coefficients agreement 2 3. Lately, model-based corpus have proven better at all three tasks. But there has been relatively little work comparing them on the same datasets. This paper aims to fill this gap by analyzing six models annotation,...
Social media have become an integral part of our lives, expanding interlinking capabilities to new levels. There is plenty be said about their positive effects. On the other hand, however, some serious negative implications social been repeatedly highlighted in recent years, pointing at various threats society and its more vulnerable members, such as teenagers, particular, ranging from much-discussed problems digital addiction polarization manipulative influences algorithms further...
George Giannakopoulos, Jeff Kubina, John Conroy, Josef Steinberger, Benoit Favre, Mijail Kabadjov, Udo Kruschwitz, Massimo Poesio. Proceedings of the 16th Annual Meeting Special Interest Group on Discourse and Dialogue. 2015.
Chatbots that can automatically answer customer requests have become a common feature on e-commerce Web sites. There are many factors might affect overall satisfaction with such services. We explore how adding language style to chatbots be used increase user satisfaction, perceived product value, interest in product, and engagement chatbot service. conducted an experimental pilot study, where two were sell theatre tickets: one communicating modern English Shakespearean-style dialect. 169...
Massimo Poesio, Jon Chamberlain, Silviu Paun, Juntao Yu, Alexandra Uma, Udo Kruschwitz. Proceedings of the 2019 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.
Aspect sentiment quadruple prediction (ASQP) facilitates a detailed understanding of opinions expressed in text by identifying the opinion term, aspect category and polarity for each opinion. However, annotating full set training examples to fine-tune models ASQP is resource-intensive process. In this study, we explore capabilities large language (LLMs) zero- few-shot learning on task across five diverse datasets. We report F1 scores slightly below those obtained with state-of-the-art...
In this report we describe the outcome of First International Workshop on Professional Search, held in co-location with SIGIR 2018. The workshop addressed specific requirements and challenges professional search, as opposed to web search. included a survey among 113 searchers, two keynote talks, six short paper break-out sessions. From all parts workshop, concluded that (1) can define search set common characteristics; but (2) there are definitely differences between domains; (3) need more...