Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the
deep representations in the hyperbolic space provide high fidelity embeddings with few …

Abstract Representation learning has become an invaluable approach for learning from
symbolic data such as text and graphs. However, state-of-the-art embedding methods …

The widespread success of large language models (LLMs) has been met with skepticism
that they possess anything like human concepts or meanings. Contrary to claims that LLMs …

Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical
structure that the next generation of unsupervised learned word embeddings should reveal …

Abstract We present Attract-Repel, an algorithm for improving the semantic quality of word
vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the …

Natural language text exhibits hierarchical structure in a variety of respects. Ideally, we could
incorporate our prior knowledge of this hierarchical structure into unsupervised learning …

Methods for unsupervised hypernym detection may broadly be categorized according to two
paradigms: pattern-based and distributional methods. In this paper, we study the …

While one of the first steps in many NLP systems is selecting what pre-trained word
embeddings to use, we argue that such a step is better left for neural networks to figure out …

We present LEAR (Lexical Entailment Attract-Repel), a novel post-processing method that
transforms any input word vector space to emphasise the asymmetric relation of lexical …

We present a novel neural model HyperVec to learn hierarchical embeddings for hypernymy
detection and directionality. While previous embeddings have shown limitations on …