2017 HighRiskLearningAcquiringNewWor

(Herbelot & Baroni, 2017) ⇒ Aelie 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 (EMNLP 2017).

Subject Headings: Distributional Semantics Models; OOV; OOV Modelling System, Herbelot-Baroni Distributional Semantics Model.

Notes

Cited By

Google Scholar: ~ 58 Citations.

Quotes

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.

References

BibTeX

@inproceedings{2017_HighRiskLearningAcquiringNewWor,
  author    = {Aelie Herbelot and
               Marco Baroni},
  editor    = {Martha Palmer and
               Rebecca Hwa and
               Sebastian Riedel},
  title     = {High-risk learning: acquiring new word vectors from tiny data},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural
               Language Processing (EMNLP 2017)},
  pages     = {304--309},
  publisher = {Association for Computational Linguistics},
  year      = {2017},
  url       = {https://doi.org/10.18653/v1/d17-1030},
  doi       = {10.18653/v1/d17-1030},
}

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2017 HighRiskLearningAcquiringNewWor	Marco Baroni Aelie Herbelot			High-risk Learning: Acquiring New Word Vectors from Tiny Data						2017