par2hier: towards vector representations for hierarchical content
| Autor: | Tommaso Teofili |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Hierarchy (mathematics)
Computer science business.industry 02 engineering and technology Function (mathematics) computer.software_genre Semantics 030507 speech-language pathology & audiology 03 medical and health sciences Node (computer science) 0202 electrical engineering electronic engineering information engineering General Earth and Planetary Sciences 020201 artificial intelligence & image processing Word2vec Artificial intelligence Paragraph 0305 other medical science business computer Natural language processing Word (computer architecture) General Environmental Science |
| Zdroj: | ICCS |
| ISSN: | 1877-0509 |
| Popis: | Word embeddings have received a lot of attention in the natural language processing area for their capabilities of capturing inner words semantics (e.g. word2vec, GloVe). The need of catching semantics at a higher and more abstract level led to creation of models like paragraph vectors for sentences and documents, seq2vec for biological sequences. In this paper we illustrate an approach for creating vector representations for hierarchical content where each node in the hierarchy is represented as a (recursive) function of its paragraph vector and the hierarchical vectors of its child nodes, computed via matrix factorization. We evaluate the effectiveness of our solution against flat paragraph vectors on a text categorization task obtaining significant µF1 improvements. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|