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.- Anthology ID:
- D17-1030
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 304–309
- Language:
- URL:
- https://aclanthology.org/D17-1030
- DOI:
- 10.18653/v1/D17-1030
- Cite (ACL):
- Aurélie Herbelot and Marco Baroni. 2017. High-risk learning: acquiring new word vectors from tiny data. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 304–309, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- High-risk learning: acquiring new word vectors from tiny data (Herbelot & Baroni, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/landing_page/D17-1030.pdf
- Code
- minimalparts/nonce2vec