Hyperbolic sentence representations for solving Textual Entailment
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916297329082368 |
|---|---|
| author | Petrovski, Igor |
| author_facet | Petrovski, Igor |
| contents | Hyperbolic spaces have proven to be suitable for modeling data of hierarchical nature. As such we use the Poincare ball to embed sentences with the goal of proving how hyperbolic spaces can be used for solving Textual Entailment. To this end, apart from the standard datasets used for evaluating textual entailment, we developed two additional datasets. We evaluate against baselines of various backgrounds, including LSTMs, Order Embeddings and Euclidean Averaging, which comes as a natural counterpart to representing sentences into the Euclidean space. We consistently outperform the baselines on the SICK dataset and are second only to Order Embeddings on the SNLI dataset, for the binary classification version of the entailment task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_15472 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperbolic sentence representations for solving Textual Entailment Petrovski, Igor Computation and Language Artificial Intelligence Machine Learning Hyperbolic spaces have proven to be suitable for modeling data of hierarchical nature. As such we use the Poincare ball to embed sentences with the goal of proving how hyperbolic spaces can be used for solving Textual Entailment. To this end, apart from the standard datasets used for evaluating textual entailment, we developed two additional datasets. We evaluate against baselines of various backgrounds, including LSTMs, Order Embeddings and Euclidean Averaging, which comes as a natural counterpart to representing sentences into the Euclidean space. We consistently outperform the baselines on the SICK dataset and are second only to Order Embeddings on the SNLI dataset, for the binary classification version of the entailment task. |
| title | Hyperbolic sentence representations for solving Textual Entailment |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.15472 |