Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929533923360768 |
|---|---|
| author | Yamagiwa, Hiroaki Takase, Yusuke Shimodaira, Hidetoshi |
| author_facet | Yamagiwa, Hiroaki Takase, Yusuke Shimodaira, Hidetoshi |
| contents | Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (ICA) is identified as an effective solution. ICA-transformed word embeddings reveal interpretable semantic axes; however, the order of these axes are arbitrary. In this study, we focus on this property and propose a novel method, Axis Tour, which optimizes the order of the axes. Inspired by Word Tour, a one-dimensional word embedding method, we aim to improve the clarity of the word embedding space by maximizing the semantic continuity of the axes. Furthermore, we show through experiments on downstream tasks that Axis Tour yields better or comparable low-dimensional embeddings compared to both PCA and ICA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06112 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings Yamagiwa, Hiroaki Takase, Yusuke Shimodaira, Hidetoshi Computation and Language Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (ICA) is identified as an effective solution. ICA-transformed word embeddings reveal interpretable semantic axes; however, the order of these axes are arbitrary. In this study, we focus on this property and propose a novel method, Axis Tour, which optimizes the order of the axes. Inspired by Word Tour, a one-dimensional word embedding method, we aim to improve the clarity of the word embedding space by maximizing the semantic continuity of the axes. Furthermore, we show through experiments on downstream tasks that Axis Tour yields better or comparable low-dimensional embeddings compared to both PCA and ICA. |
| title | Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.06112 |