Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

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

  • Herbelot, Aurélie
  • Baroni, Marco
Comunicació presentada a: 2017 Conference on Empirical Methods in Natural Language Processing celebrat del 7 al 11 de setembre de 2017 a Copenhaguen, Dinamarca., 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., We acknowledge ERC 2011 Starting Independent Research Grant No 283554 (COMPOSES). This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 751250.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

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

  • Herbelot, Aurélie
  • Baroni, Marco
Comunicació presentada a: 2017 Conference on Empirical Methods in Natural Language Processing celebrat del 7 al 11 de setembre de 2017 a Copenhaguen, Dinamarca., 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., We acknowledge ERC 2011 Starting Independent Research Grant No 283554 (COMPOSES). This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 751250.