Multilingual Models for Compositional Distributed Semantics

@inproceedings{Hermann2014MultilingualMF,
  title={Multilingual Models for Compositional Distributed Semantics},
  author={Karl Moritz Hermann and Phil Blunsom},
  booktitle={ACL},
  year={2014}
}
  • Karl Moritz Hermann, Phil Blunsom
  • Published in ACL 2014
  • Computer Science
  • We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of semantically equivalent sentences, while maintaining sufficient distance between those of dissimilar sentences. The models do not rely on word alignments or any syntactic information and are successfully applied to a number of diverse languages. We extend… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 223 CITATIONS

    On Zero-shot Cross-lingual Transfer of Multilingual Neural Machine Translation

    • 2018
    VIEW 4 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Learning Monolingual Compositional Representations via Bilingual Supervision

    VIEW 11 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Sparse Bilingual Word Representations for Cross-lingual Lexical Entailment

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Toward any-language zero-shot topic classification of textual documents

    VIEW 12 EXCERPTS
    CITES METHODS, BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    Bilingual Word Embeddings from Parallel and Non-parallel Corpora for Cross-Language Text Classification

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Classifying Educational Lectures in Low-Resource Languages

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence

    VIEW 5 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Bilingual Word Representations with Monolingual Quality in Mind

    VIEW 4 EXCERPTS
    CITES RESULTS & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2013
    2020

    CITATION STATISTICS

    • 18 Highly Influenced Citations

    • Averaged 41 Citations per year from 2017 through 2019

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES

    Natural Language Processing (Almost) from Scratch

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Latent Dirichlet Allocation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Neural Probabilistic Language Model

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL