A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866907817189834752 |
|---|---|
| author | Zaland, Obaidullah Abulaish, Muhammad Fazil, Mohd. |
| author_facet | Zaland, Obaidullah Abulaish, Muhammad Fazil, Mohd. |
| contents | Vector-based word representations help countless Natural Language Processing (NLP) tasks capture the language's semantic and syntactic regularities. In this paper, we present the characteristics of existing word embedding approaches and analyze them with regard to many classification tasks. We categorize the methods into two main groups - Traditional approaches mostly use matrix factorization to produce word representations, and they are not able to capture the semantic and syntactic regularities of the language very well. On the other hand, Neural-network-based approaches can capture sophisticated regularities of the language and preserve the word relationships in the generated word representations. We report experimental results on multiple classification tasks and highlight the scenarios where one approach performs better than the rest. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_07196 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches Zaland, Obaidullah Abulaish, Muhammad Fazil, Mohd. Computation and Language Neural and Evolutionary Computing Vector-based word representations help countless Natural Language Processing (NLP) tasks capture the language's semantic and syntactic regularities. In this paper, we present the characteristics of existing word embedding approaches and analyze them with regard to many classification tasks. We categorize the methods into two main groups - Traditional approaches mostly use matrix factorization to produce word representations, and they are not able to capture the semantic and syntactic regularities of the language very well. On the other hand, Neural-network-based approaches can capture sophisticated regularities of the language and preserve the word relationships in the generated word representations. We report experimental results on multiple classification tasks and highlight the scenarios where one approach performs better than the rest. |
| title | A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches |
| topic | Computation and Language Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2303.07196 |