2016

Swivel: Improving Embeddings by Noticing What's Missing

Shazeer, Noam, Doherty, Ryan, Evans, Colin et al.

Understand

We present Submatrix-wise Vector Embedding Learner (Swivel), a method for generating low-dimensional feature embeddings from a feature co-occurrence matrix.

  • Swivel performs approximate factorization of the point-wise mutual information matrix via stochastic gradient descent.
  • It uses a piecewise loss with special handling for unobserved co-occurrences, and thus makes use of all the information in the matrix.
  • While this requires computation proportional to the size of the entire matrix, we make use of vectorized multiplication to process thousands of rows and columns at once to compute millions of predicted values.

Built on

  • Placing search in context: The concept revisited

    Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Eytan Ruppin · 2001

    Earlier work this paper cites.

  • Collaborative filtering for implicit feedback datasets

    Yifan Hu, Yehuda Koren, and Chris Volinsky · 2008

    Earlier work this paper cites.

  • Using wiktionary for computing semantic relatedness

    Original

    Torsten Zesch, Christof Müller, and Iryna Gurevych · 2008

    Earlier work this paper cites.

  • A study on similarity and relatedness using distributional and wordnet-based approaches

    Eneko Agirre, Enrique Alfonseca, Keith Hall, Jana Kravalova, Marius Paşca, and Aitor Soroa · 2009

    Earlier work this paper cites.

  • Adaptive subgradient methods for online learning and stochastic optimization

    John Duchi, Elad Hazan, and Yoram Singer · 2011

    Earlier work this paper cites.

Similar

  • A word at a time: computing word relatedness using temporal semantic analysis

    Kira Radinsky, Eugene Agichtein, Evgeniy Gabrilovich, and Shaul Markovitch · 2011

    Cited alongside, same era.

  • Hogwild: A lock-free approach to parallelizing stochastic gradient descent

    Benjamin Recht, Christopher Re, Stephen Wright, and Feng Niu · 2011

    Cited alongside, same era.

  • Distributional semantics in technicolor

    Elia Bruni, Gemma Boleda, Marco Baroni, and Nam-Khanh Tran · 2012

    Cited alongside, same era.

  • Large scale distributed deep networks

    Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Andrew Senior, Paul Tucker, Ke Yang, Quoc V Le, et al · 2012

    Cited alongside, same era.

  • Better word representations with recursive neural networks for morphology

    Minh-Thang Luong, Richard Socher, and Christopher D Manning · 2013

    Cited alongside, same era.

  • Efficient estimation of word representations in vector space

    Original

    Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean

    Cited in the paper.

  • Linguistic regularities in continuous space word representations

    Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig

    Cited in the paper.

Then

  • Don’t count, predict! a systematic comparison of context-counting vs. context-predicting semantic vectors

    Marco Baroni, Georgiana Dinu, and Germán Kruszewski · 2014

    Later among the works it cites.

  • Simlex-999: Evaluating semantic models with (genuine) similarity estimation

    Original

    Felix Hill, Roi Reichart, and Anna Korhonen · 2014

    Later among the works it cites.

  • Neural word embedding as implicit matrix factorization

    Omer Levy and Yoav Goldberg · 2014

    Later among the works it cites.

  • Glove: Global vectors for word representation

    Jeffrey Pennington, Richard Socher, and Christopher D Manning · 2014

    Later among the works it cites.

  • Improving distributional similarity with lessons learned from word embeddings

    Omer Levy, Yoav Goldberg, and Ido Dagan · 2015

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…