mlsanityData to 7 Oct 2026

High-risk learning: acquiring new word vectors from tiny data

arXiv 1707.06556 ↗First posted 20 Jul 2017cs.CL cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 2; 2023: 0; 2024: 3; 2025: 1; 2026: 1.

13 papers.

Sort:

  1. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  2. 2021Dynamic Language Models for Continuously Evolving Contentcited by 27
  3. 2021Recent Trends in Named Entity Recognition (NER)cited by 9
  4. 2024The Impact of Word Splitting on the Semantic Content of Contextualized Word Representationscited by 6
  5. 2021Lacking the embedding of a word? Look it up into a traditional dictionarycited by 4
  6. 2025Rapid Word Learning Through Meta In-Context Learningcited by 4
  7. 2024CoLLEGe: Concept Embedding Generation for Large Language Modelscited by 3
  8. 2024Measuring Contextual Informativeness in Child-Directed Textcited by 3
  9. 2021Trajectory-Based Meta-Learning for Out-Of-Vocabulary Word Embedding Learningcited by 0
  10. 2021Novel Aficionados and Doppelg"angers: a referential task for semantic representations of individual entitiescited by 0
  11. 2022An Attention-Based Model for Predicting Contextual Informativeness and Curriculum Learning Applicationscited by 0
  12. 2022Using dependency parsing for few-shot learning in distributional semanticscited by 0
1 more
  1. 2026Dynamics of Meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhalacited by 0