Papers by Michael Bugert
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution (P19-1)
Copied to clipboard
| Challenge: | Recognizing that various textual spans across multiple texts refer to the same entity or event is an important NLP task. |
| Approach: | They propose a neural architecture for cross-document coreference resolution by representing an event mention using its lexical span, surrounding context, and relation to other mentions via predicate-arguments structures. |
| Outcome: | The proposed model outperforms the state-of-the-art event coreference model on ECB+ while providing the first entity coreference results on this corpus. |
The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation (C18-2)
Copied to clipboard
| Challenge: | INCEpTION is an annotation platform for interactive and semantic annotation . the platform is both generic and modular . |
| Approach: | INCEpTION is an annotation platform for interactive and semantic annotation . the platform incorporates machine learning capabilities which actively assist annotators . |
| Outcome: | INCEpTION is an open-source annotation platform for tasks including interactive and semantic annotation. |
Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online News (2021.emnlp-main)
Copied to clipboard
| Challenge: | Annotating CDCR data is laborious and expensive, explaining why existing corpora are small and lack domain coverage. |
| Approach: | They use hyperlinks to extract event coreference data from online news articles . they find that models trained on small subsets of HyperCoref are highly competitive . |
| Outcome: | The proposed system frees up CDCR research from costly human-annotated training data and opens up possibilities beyond English. |