# Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces

arXiv: https://arxiv.org/abs/1811.04983 · HTML: https://mlsanity.com/paper/1811.04983/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations](https://mlsanity.com/paper/2402.14616/) (2024)
- [Lacking the embedding of a word? Look it up into a traditional dictionary](https://mlsanity.com/paper/2109.11763/) (2021)

## Abstract (arXiv)

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as WordNet, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. We show that the approach can provide consistent performance improvements across multiple evaluation benchmarks: in-vitro, on multiple rare word similarity datasets, and in-vivo, in two downstream text classification tasks.