no code implementations • ACL (WOAH) 2021 • Samira Zad, Joshuan Jimenez, Mark Finlayson
There have been several attempts to create an accurate and thorough emotion lexicon in English, which identifies the emotional content of words.
no code implementations • LREC 2022 • Mustafa Ocal, Antonela Radas, Jared Hummer, Karine Megerdoomian, Mark Finlayson
TimeML is an annotation scheme for capturing temporal information in text.
no code implementations • EMNLP 2021 • Labiba Jahan, Rahul Mittal, Mark Finlayson
Stereotypical character roles-also known as archetypes or dramatis personae-play an important function in narratives: they facilitate efficient communication with bundles of default characteristics and associations and ease understanding of those characters’ roles in the overall narrative.
no code implementations • LREC 2022 • Mustafa Ocal, Adrian Perez, Antonela Radas, Mark Finlayson
TimeML is a scheme for representing temporal information (times, events, & temporal relations) in texts.
no code implementations • COLING 2020 • Mohammed Aldawsari, Adrian Perez, Deya Banisakher, Mark Finlayson
Determining whether an event in a news article is a foreground or background event would be useful in many natural language processing tasks, for example, temporal relation extraction, summarization, or storyline generation.
no code implementations • COLING 2020 • Labiba Jahan, Rahul Mittal, W. Victor Yarlott, Mark Finlayson
One of the most fundamental elements of narrative is character: if we are to understand a narrative, we must be able to identify the characters of that narrative.
no code implementations • WS 2020 • Samira Zad, Mark Finlayson
Close inspection of that work, however, revealed significant reproducibility problems, and we were unable to reimplement Kim{'}s approach as described.
no code implementations • WS 2020 • Deya Banisakher, W. Victor Yarlott, Mohammed Aldawsari, Naphtali Rishe, Mark Finlayson
Identifying the discourse structure of documents is an important task in understanding written text.
no code implementations • WS 2020 • Andres Cremisini, Mark Finlayson
Cross-Document Event Coreference (CDEC) is the task of finding coreference relationships between events in separate documents, most commonly assessed using the Event Coreference Bank+ corpus (ECB+).
no code implementations • LREC 2020 • Mustafa Ocal, Mark Finlayson
Temporal Dependency Trees (TDTs) have emerged as an alternative to full temporal graphs for representing the temporal structure of texts, with a key advantage being that TDTs can be straightforwardly computed using adapted dependency parsers.
no code implementations • ACL 2019 • Mohammed Aldawsari, Mark Finlayson
Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding.
no code implementations • WS 2019 • Labiba Jahan, Mark Finlayson
The most important of the two corpora is a set of 46 Russian folktales, on which the model achieves an F1 of 0. 81.
no code implementations • COLING 2018 • W. Victor Yarlott, Cristina Cornelio, Tian Gao, Mark Finlayson
We test two hypotheses: first, that people can reliably annotate news articles with van Dijk{'}s theory; second, that we can reliably predict these labels using machine learning.
no code implementations • COLING 2018 • Labiba Jahan, Geeticka Chauhan, Mark Finlayson
The system achieves an F1 of 0. 88 for classifying the animacy of referring expressions, which is comparable to state of the art results for classifying the animacy of words, and achieves an F1 of 0. 75 for classifying the animacy of coreference chains themselves.
no code implementations • EMNLP 2017 • Joshua Eisenberg, Mark Finlayson
Story detection is the task of determining whether or not a unit of text contains a story.
no code implementations • LREC 2014 • Mark Finlayson, Jeffry Halverson, Steven Corman
We describe the N2 (Narrative Networks) Corpus, a new language resource.