Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910840500781056 |
|---|---|
| author | Shrestha, Gyanendra Jiang, Chutain Akula, Sai Yannam, Vivek Pyayt, Anna Gubanov, Michael |
| author_facet | Shrestha, Gyanendra Jiang, Chutain Akula, Sai Yannam, Vivek Pyayt, Anna Gubanov, Michael |
| contents | Embeddings serve as condensed vector representations for real-world entities, finding applications in Natural Language Processing (NLP), Computer Vision, and Data Management across diverse downstream tasks. Here, we introduce novel specialized embeddings optimized, and explicitly tailored to encode the intricacies of complex 2-D context in tables, featuring horizontal, vertical hierarchical metadata, and nesting. To accomplish that we define the Bi-dimensional tabular coordinates, separate horizontal, vertical metadata and data contexts by introducing a new visibility matrix, encode units and nesting through the embeddings specifically optimized for mimicking intricacies of such complex structured data. Through evaluation on 5 large-scale structured datasets and 3 popular downstream tasks, we observed that our solution outperforms the state-of-the-art models with the significant MAP delta of up to 0.28. GPT-4 LLM+RAG slightly outperforms us with MRR delta of up to 0.1, while we outperform it with the MAP delta of up to 0.42. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15819 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting Shrestha, Gyanendra Jiang, Chutain Akula, Sai Yannam, Vivek Pyayt, Anna Gubanov, Michael Computation and Language Artificial Intelligence Machine Learning Embeddings serve as condensed vector representations for real-world entities, finding applications in Natural Language Processing (NLP), Computer Vision, and Data Management across diverse downstream tasks. Here, we introduce novel specialized embeddings optimized, and explicitly tailored to encode the intricacies of complex 2-D context in tables, featuring horizontal, vertical hierarchical metadata, and nesting. To accomplish that we define the Bi-dimensional tabular coordinates, separate horizontal, vertical metadata and data contexts by introducing a new visibility matrix, encode units and nesting through the embeddings specifically optimized for mimicking intricacies of such complex structured data. Through evaluation on 5 large-scale structured datasets and 3 popular downstream tasks, we observed that our solution outperforms the state-of-the-art models with the significant MAP delta of up to 0.28. GPT-4 LLM+RAG slightly outperforms us with MRR delta of up to 0.1, while we outperform it with the MAP delta of up to 0.42. |
| title | Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.15819 |