Hyperbolic sentence representations for solving Textual Entailment
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationNatural Language InferenceSentenceSimilar Papers 제목 키워드 기반
Compositional Entailment Learning for Hyperbolic Vision-Language Models
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and textual concepts ar…
Language ModellingRepresentation LearningSentenceHyperbolic Neural Networks
Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par w…
Graph Representation LearningNatural Language InferenceSentenceSentence EmbeddingsMultimodal Logical Inference System for Visual-Textual Entailment
A large amount of research about multimodal inference across text and vision has been recently developed to obtain visually grounded word and sentence representations. In this paper, we use logic-based representations as…
Automated Theorem ProvingNatural Language InferenceSemantic ParsingSentenceLearning Entailment-Based Sentence Embeddings from Natural Language Inference
Large datasets on natural language inference are a potentially valuable resource for inducing semantic representations of natural language sentences. But in many such models the embeddings computed by the sentence encod…
Inductive BiasNatural Language InferenceSentenceSentence EmbeddingsHyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions (>77 tokens) due to absolute positional encoding and pretraining on …
Long-Context UnderstandingCross-Modal Retrieval