# Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

arXiv: https://arxiv.org/abs/1805.03228 · HTML: https://mlsanity.com/paper/1805.03228/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2018.

## Built on by (most cited first, 6 of 6)

- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations](https://mlsanity.com/paper/2108.12941/) (2021)
- [SexWEs: Domain-Aware Word Embeddings via Cross-lingual Semantic Specialisation for Chinese Sexism Detection in Social Media](https://mlsanity.com/paper/2211.08447/) (2022)
- [Revisiting the Prepositional-Phrase Attachment Problem Using Explicit Commonsense Knowledge](https://mlsanity.com/paper/2102.00924/) (2021)
- [Massively Multilingual Lexical Specialization of Multilingual Transformers](https://mlsanity.com/paper/2208.01018/) (2022)
- [Domain Lexical Knowledge-based Word Embedding Learning for Text Classification under Small Data](https://mlsanity.com/paper/2506.01621/) (2025)

## Abstract (arXiv)

Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as WordNet. By design, these post-processing methods only update the vectors of words occurring in external lexicons, leaving the representations of all unseen words intact. In this paper, we show that constraint-driven vector space specialisation can be extended to unseen words. We propose a novel post-specialisation method that: a) preserves the useful linguistic knowledge for seen words; while b) propagating this external signal to unseen words in order to improve their vector representations as well. Our post-specialisation approach explicits a non-linear specialisation function in the form of a deep neural network by learning to predict specialised vectors from their original distributional counterparts. The learned function is then used to specialise vectors of unseen words. This approach, applicable to any post-processing model, yields considerable gains over the initial specialisation models both in intrinsic word similarity tasks, and in two downstream tasks: dialogue state tracking and lexical text simplification. The positive effects persist across three languages, demonstrating the importance of specialising the full vocabulary of distributional word vector spaces.