SemEval-2010 Task 8

Intra-sentence No Polarity Signal No Strength Signal

SemEval-2010 Task 8 defines nine semantic relations between nominal pairs (including Cause-Effect) and asks systems to classify the relation and its directionality from a short context sentence.

causal-candidate-extraction is derived from the identification table above (causalatee.data.utils.identification_batch_to_extraction), restricted to the entities backing an actual causal relation — UniCausal's SemEval-2010 Task 8 CSVs don't carry span data for a standalone extraction table.

Overview

Domain	General
Year	2010
Sentences	10,690
Granularity	Intra-sentence

Tasks & Splits

Task	Train	Test
Causality Detection	7,975	2,715
Causal Event Candidate Extraction	999	328
Causality Identification	7,975	2,715
Causality Extraction	—	—

Data Explorer

Causality Detection

Causal Event Candidate Extraction

Causality Identification

Citation

@inproceedings{hendrickx:2010,
  title      = {{{SemEval-2010 Task}} 8: {{Multi-Way Classification}} of {{Semantic Relations}} between {{Pairs}} of {{Nominals}}},
  shorttitle = {{{SemEval-2010 Task}} 8},
  booktitle  = {Proceedings of the 5th {{International Workshop}} on {{Semantic Evaluation}}, {{SemEval}}@{{ACL}} 2010, {{Uppsala University}}, {{Uppsala}}, {{Sweden}}, {{July}} 15-16, 2010},
  author     = {Hendrickx, Iris and Kim, Su Nam and Kozareva, Zornitsa and Nakov, Preslav and S{\'e}aghdha, Diarmuid {\'O} and Pad{\'o}, Sebastian and Pennacchiotti, Marco and Romano, Lorenza and Szpakowicz, Stan},
  editor     = {Erk, Katrin and Strapparava, Carlo},
  year       = 2010,
  pages      = {33--38},
  publisher  = {The Association for Computer Linguistics},
  urldate    = {2024-08-26}
}