Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2019
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911596820824064 |
|---|---|
| author | Govindarajan, Venkata Subrahmanyan Van Durme, Benjamin White, Aaron Steven |
| author_facet | Govindarajan, Venkata Subrahmanyan Van Durme, Benjamin White, Aaron Steven |
| contents | We present a novel semantic framework for modeling linguistic expressions of generalization---generic, habitual, and episodic statements---as combinations of simple, real-valued referential properties of predicates and their arguments. We use this framework to construct a dataset covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to probe the efficacy of type-level and token-level information---including hand-engineered features and static (GloVe) and contextual (ELMo) word embeddings---for predicting expressions of generalization. Data and code are available at decomp.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1901_11429 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements Govindarajan, Venkata Subrahmanyan Van Durme, Benjamin White, Aaron Steven Computation and Language We present a novel semantic framework for modeling linguistic expressions of generalization---generic, habitual, and episodic statements---as combinations of simple, real-valued referential properties of predicates and their arguments. We use this framework to construct a dataset covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to probe the efficacy of type-level and token-level information---including hand-engineered features and static (GloVe) and contextual (ELMo) word embeddings---for predicting expressions of generalization. Data and code are available at decomp.io. |
| title | Decomposing Generalization: Models of Generic, Habitual, and Episodic Statements |
| topic | Computation and Language |
| url | https://arxiv.org/abs/1901.11429 |