Initial release of nonce2vec.

This is the repo accompanying the paper "High-risk learning: acquiring new word vectors from tiny data" (Herbelot & Baroni, 2017).

Abstract

Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn 'a good vector' for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task involving 2-6 sentences' worth of context, showing a large increase in performance over state-of-the-art models on the definitional task.

Citation

A. Herbelot and M. Baroni. 2017. High-risk learning: Acquiring new word vectors from tiny data. Proceedings of EMNLP 2017 (Conference on Empirical Methods in Natural Language Processing).