CEO: Corpus-based Open-Domain Event Ontology Induction
Not on the map. Why?
Abstract (arXiv)
Existing event-centric NLP models often only apply to the pre-defined ontology, which significantly restricts their generalization capabilities. This paper presents CEO, a novel Corpus-based Event Ontology induction model to relax the restriction imposed by pre-defined event ontologies. Without direct supervision, CEO leverages distant supervision from available summary datasets to detect corpus-wise salient events and exploits external event knowledge to force events within a short distance to have close embeddings. Experiments on three popular event datasets show that the schema induced by CEO has better coverage and higher accuracy than previous methods. Moreover, CEO is the first event ontology induction model that can induce a hierarchical event ontology with meaningful names on eleven open-domain corpora, making the induced schema more trustworthy and easier to be further curated.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 65 references that are in the map. First posted on arXiv 22 May 2023.
Builds on
20 of 65 references.
References · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
- 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
- 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 103
- 2021DEGREE: A Data-Efficient Generation-Based Event Extraction Modelcited by 82
- 2019Multi-Sentence Argument Linkingcited by 80
8 more
- 2020From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clusteringcited by 65
- 2015A cost function for similarity-based hierarchical clusteringcited by 63
- 2022Summarization as Indirect Supervision for Relation Extractioncited by 31
- 2021Query and Extract: Refining Event Extraction as Type-oriented Binary Decodingcited by 26
- 2021Corpus-based Open-Domain Event Type Inductioncited by 17
- 2018Automatic Event Salience Identificationcited by 14
- 2018An Improved Cost Function for Hierarchical Cluster Treescited by 10
- 2022Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attentioncited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.