Hyperbolic sentence representations for solving Textual Entailment
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 8 of its 29 references that are in the map. First posted on arXiv 15 Jun 2024.
Builds on
8 of 29 references.
References · 8
- 2015A large annotated corpus for learning natural language inferencecited by 1,847
- 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 432
- 2015Order-Embeddings of Images and Languagecited by 113
- 2017Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Featurescited by 104
- 2015Reasoning about Entailment with Neural Attentioncited by 69
- 2015Learning Natural Language Inference with LSTMcited by 51
- 2016Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attentioncited by 23
- 2016Siamese CBOW: Optimizing Word Embeddings for Sentence Representationscited by 10
Built on by
Citing papers per year: 2025: 2.
2 papers.