Steve Fonin Mbouadeu
Steve Fonin Mbouadeu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Asim Abbas
St. John’s University
1 shared publication - Fazel Keshtkar
St. John’s University
1 shared publication - Hasan Ali Khattak
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST), Islamabad, Pakistan
1 shared publication - Ken Barker
IBM Research
1 shared publication - Martin Lorenzo
University IBM Research IBM Research IBM Research
1 shared publication - Oktie Hassanzadeh
KAIST IBM Research
1 shared publication
Latest Publications
- Open Access
An Evaluation Framework for Mapping News Headlines to Event Classes in a Knowledge Graph
Mapping ongoing news headlines to event-related classes in a rich knowledge base can be an important component in a knowledge-based event analysis and forecasting solution. In this paper, we present a methodology for creating a benchmark dataset of news headlines mapped to event classes in Wikidata, and resources for the evaluation of methods that perform the mapping. We use the dataset to study two classes of unsupervised methods for this task: 1) adaptations of classic entity linking methods, and 2) methods that treat the problem as a zero-shot text classification problem. For the first approach, we evaluate off-the-shelf entity linking systems. For the second approach, we explore a) pre-trained natural language inference (NLI) models, and b) pre-trained large generative language models. We present the results of our evaluation, lessons learned, and directions for future work. The dataset and scripts for evaluation are made publicly available.
Open AccessAn Evaluation Framework for Mapping News Headlines to Event Classes in a Knowledge Graph
Mapping ongoing news headlines to event-related classes in a rich knowledge base can be an important component in a knowledge-based event analysis and forecasting solution. In this paper, we present a methodology for creating a benchmark dataset of news headlines mapped to event classes in Wikidata, and resources for the evaluation of methods that perform the mapping. We use the dataset to study two classes of unsupervised methods for this task: 1) adaptations of classic entity linking methods, and 2) methods that treat the problem as a zero-shot text classification problem. For the first approach, we evaluate off-the-shelf entity linking systems. For the second approach, we explore a) pre-trained natural language inference (NLI) models, and b) pre-trained large generative language models. We present the results of our evaluation, lessons learned, and directions for future work. The dataset and scripts for evaluation are made publicly available.
- 2 February 2023
- Published by Springer Nature
- p. 75-86
A Decentralized Environment for Biomedical Semantic Content Authoring and Publishing
- 2 February 2023
- Published by Springer Nature
- p. 75-86
A Decentralized Environment for Biomedical Semantic Content Authoring and Publishing