Using Images to Find Context-Independent Word Representations in Vector Space
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915049211166720 |
|---|---|
| author | Kumar, Harsh |
| author_facet | Kumar, Harsh |
| contents | Many methods have been proposed to find vector representation for words, but most rely on capturing context from the text to find semantic relationships between these vectors. We propose a novel method of using dictionary meanings and image depictions to find word vectors independent of any context. We use auto-encoder on the word images to find meaningful representations and use them to calculate the word vectors. We finally evaluate our method on word similarity, concept categorization and outlier detection tasks. Our method performs comparably to context-based methods while taking much less training time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03592 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Using Images to Find Context-Independent Word Representations in Vector Space Kumar, Harsh Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition Many methods have been proposed to find vector representation for words, but most rely on capturing context from the text to find semantic relationships between these vectors. We propose a novel method of using dictionary meanings and image depictions to find word vectors independent of any context. We use auto-encoder on the word images to find meaningful representations and use them to calculate the word vectors. We finally evaluate our method on word similarity, concept categorization and outlier detection tasks. Our method performs comparably to context-based methods while taking much less training time. |
| title | Using Images to Find Context-Independent Word Representations in Vector Space |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03592 |