ReferenceNet: a semantic-pragmatic network for capturing reference relations.

Piek Vossen, Filip Ilievski, Marten Postrma


Abstract
In this paper, we present ReferenceNet: a semantic-pragmatic network of reference relations between synsets. Synonyms are assumed to be exchangeable in similar contexts and also word embeddings are based on sharing of local contexts represented as vectors. Co-referring words, however, tend to occur in the same topical context but in different local contexts. In addition, they may express different concepts related through topical coherence, and through author framing and perspective. In this paper, we describe how reference relations can be added to WordNet and how they can be acquired. We evaluate two methods of extracting event coreference relations using WordNet relations against a manual annotation of 38 documents within the same topical domain of gun violence. We conclude that precision is reasonable but recall is lower because the WordNet hierarchy does not sufficiently capture the required coherence and perspective relations.
Anthology ID:
2018.gwc-1.25
Volume:
Proceedings of the 9th Global Wordnet Conference
Month:
January
Year:
2018
Address:
Nanyang Technological University (NTU), Singapore
Editors:
Francis Bond, Piek Vossen, Christiane Fellbaum
Venue:
GWC
SIG:
SIGLEX
Publisher:
Global Wordnet Association
Note:
Pages:
219–228
Language:
URL:
https://aclanthology.org/2018.gwc-1.25
DOI:
Bibkey:
Cite (ACL):
Piek Vossen, Filip Ilievski, and Marten Postrma. 2018. ReferenceNet: a semantic-pragmatic network for capturing reference relations.. In Proceedings of the 9th Global Wordnet Conference, pages 219–228, Nanyang Technological University (NTU), Singapore. Global Wordnet Association.
Cite (Informal):
ReferenceNet: a semantic-pragmatic network for capturing reference relations. (Vossen et al., GWC 2018)
Copy Citation:
PDF:
https://aclanthology.org/2018.gwc-1.25.pdf
Data
ECB+