Self-supervised Topic Taxonomy Discovery in the Box Embedding Space
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913481949708288 |
|---|---|
| author | Lu, Yuyin Chen, Hegang Mao, Pengbo Rao, Yanghui Xie, Haoran Wang, Fu Lee Li, Qing |
| author_facet | Lu, Yuyin Chen, Hegang Mao, Pengbo Rao, Yanghui Xie, Haoran Wang, Fu Lee Li, Qing |
| contents | Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them. Unfortunately, most of prior work can hardly model semantic scopes of words and topics by holding the Euclidean embedding space assumption. What's worse, they infer asymmetric hierarchical relations by symmetric distances between topic embeddings. As a result, existing methods suffer from problems of low-quality topics at high abstraction levels and inaccurate hierarchical relations. To alleviate these problems, this paper develops a Box embedding-based Topic Model (BoxTM) that maps words and topics into the box embedding space, where the asymmetric metric is defined to properly infer hierarchical relations among topics. Additionally, our BoxTM explicitly infers upper-level topics based on correlation between specific topics through recursive clustering on topic boxes. Finally, extensive experiments validate high-quality of the topic taxonomy learned by BoxTM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15050 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised Topic Taxonomy Discovery in the Box Embedding Space Lu, Yuyin Chen, Hegang Mao, Pengbo Rao, Yanghui Xie, Haoran Wang, Fu Lee Li, Qing Computation and Language Topic taxonomy discovery aims at uncovering topics of different abstraction levels and constructing hierarchical relations between them. Unfortunately, most of prior work can hardly model semantic scopes of words and topics by holding the Euclidean embedding space assumption. What's worse, they infer asymmetric hierarchical relations by symmetric distances between topic embeddings. As a result, existing methods suffer from problems of low-quality topics at high abstraction levels and inaccurate hierarchical relations. To alleviate these problems, this paper develops a Box embedding-based Topic Model (BoxTM) that maps words and topics into the box embedding space, where the asymmetric metric is defined to properly infer hierarchical relations among topics. Additionally, our BoxTM explicitly infers upper-level topics based on correlation between specific topics through recursive clustering on topic boxes. Finally, extensive experiments validate high-quality of the topic taxonomy learned by BoxTM. |
| title | Self-supervised Topic Taxonomy Discovery in the Box Embedding Space |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.15050 |