2021
DOI: 10.48550/arxiv.2107.10326
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

COfEE: A Comprehensive Ontology for Event Extraction from text

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 0 publications
0
2
0
Order By: Relevance
“…If directly applied the existing extraction technologies to the judicial field, they will face the problem of incident type mismatch (Filtz et al, 2020;Li et al, 2020). In addition, many extraction technologies (e.g., Balali et al, 2021;Chen et al, 2015;Nguyen et al, 2016) were experimentally verified on publicly available English data sets, but in the Chinese judicial field, as far as we know, there was no standard experimental data (Feng et al, 2022). Furthermore, in Chinese divorce legal cases, there are many sentences containing multiple events that share arguments or trigger words, but most of the existing technologies are focused on extracting a single event from a single sentence (Zeng et al, 2018), which cannot solve this problem.…”
mentioning
confidence: 99%
“…If directly applied the existing extraction technologies to the judicial field, they will face the problem of incident type mismatch (Filtz et al, 2020;Li et al, 2020). In addition, many extraction technologies (e.g., Balali et al, 2021;Chen et al, 2015;Nguyen et al, 2016) were experimentally verified on publicly available English data sets, but in the Chinese judicial field, as far as we know, there was no standard experimental data (Feng et al, 2022). Furthermore, in Chinese divorce legal cases, there are many sentences containing multiple events that share arguments or trigger words, but most of the existing technologies are focused on extracting a single event from a single sentence (Zeng et al, 2018), which cannot solve this problem.…”
mentioning
confidence: 99%
“…Other related datasets that insufficiently overlap ICBe's domain for comparison include BCOW(Leng and Singer, 1988),WEIS (McClelland, 1978), CREON(Hermann, 1984), CASCON(Bloomfield and Moulton., 1989), SHERFACS(Sherman, 2000), Real-Time Phoenix(Brandt et al, 2018), and COfEE(Balali et al, 2021) (see histories inMerritt, 1994 andHall, 2006).4 See Balali et al (2021) for a recent review of ontological depth and availability of Gold Standard example text.…”
mentioning
confidence: 99%