Representing words as regions in vector space
By K. Erk. 2009
66 citations recorded by the source corpus.
Vector space models of word meaning typically represent the meaning of a word as a vector computed by summing over all its corpus occurrences. Words close to this point in space can be assumed to be similar to it in meaning. But how far around this point does the region of similar meaning extend? In this paper we discuss two models that represent word meaning as regions in vector space. Both representations can be computed from traditional point representations in vector space. We find that both models perform at over 95% F-score on a token classification task.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jure Leskovec
- Hongyu Ren
- Weihua Hu
- Percy Liang
- Andrew McCallum
- Luke Vilnis
- Ryan Cotterell
- Yoshua Bengio
Citations in the corpus
- Word Representations via Gaussian Embedding (2014, background): “In linguistic semantics, work on the distributional inclusion hypothesis (Geffet & Dagan, 2005), uses traditional count-based vectors to define regions in vector space (Erk, 2009) such that subordinate concepts are included in these regions.”
- Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings (2020, background): “…work is on structured embeddings, which associate images, words, sentences, or knowledge base concepts with geometric objects such as regions (Erk, 2009; Vilnis et al., 2018; Li et al., 2019), densities (Vilnis & McCallum, 2014; He et al., 2015; Athiwaratkun & Wilson, 2018), and orderings…”
- A Plug-and-Play Method for Controlled Text Generation (2021, background): “Notably, it has been shown that cosine similarity between word embeddings learned by algorithms like GloVe provides a metric of semantic similarity (Erk, 2009; Pennington et al., 2014).”
- Vector Space Models of Word Meaning and Phrase Meaning: A Survey (2012, background): “Erk (2009) transfers one aspect of Gärdenfors’ model to a distributional setting, the representation of words as a region rather than a point.”