Learning Concept Abstractness Using Weak Supervision
Not on the map. Why?
Abstract (arXiv)
We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data. Exploiting only minimal linguistic clues and the contextual usage of a concept as manifested in textual data, we train sufficiently powerful classifiers, obtaining high correlation with human labels. The results imply the applicability of this approach to additional properties of concepts, additional languages, and resource-scarce scenarios.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Sep 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 2; 2024: 2.
6 papers.
- 2023Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understandingcited by 19
- 2023Mitigating Open-Vocabulary Caption Hallucinationscited by 18
- 2021Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identificationcited by 0
- 2022Automatic generation of a large dictionary with concreteness/abstractness ratings based on a small human dictionarycited by 0
- 2024ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curationcited by 0
- 2024Using Letter Positional Probabilities to Assess Word Complexitycited by 0
- 2024Using Letter Positional Probabilities to Assess Word Complexity11 Apr 2024
- 2024ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation2 Mar 2024
- 2023Mitigating Open-Vocabulary Caption Hallucinations6 Dec 2023
- 2023Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding21 Mar 2023
- 2022Automatic generation of a large dictionary with concreteness/abstractness ratings based on a small human dictionary13 Jun 2022
- 2021Combining Pre-trained Word Embeddings and Linguistic Features for Sequential Metaphor Identification7 Apr 2021