Corpus ID: 207863622

How to Evaluate Word Representations of Informal Domain?

@article{Chai2019HowTE,
  title={How to Evaluate Word Representations of Informal Domain?},
  author={Yekun Chai and Naomi Saphra and Adam Lopez},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.04669}
}
  • Yekun Chai, Naomi Saphra, Adam Lopez
  • Published in ArXiv 2019
  • Computer Science
  • Diverse word representations have surged in most state-of-the-art natural language processing (NLP) applications. Nevertheless, how to efficiently evaluate such word embeddings in the informal domain such as Twitter or forums, remains an ongoing challenge due to the lack of sufficient evaluation dataset. We derived a large list of variant spelling pairs from UrbanDictionary with the automatic approaches of weakly-supervised pattern-based bootstrapping and self-training linear-chain conditional… CONTINUE READING

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

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES

    Improving Distributional Similarity with Lessons Learned from Word Embeddings

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Enriching Word Vectors with Subword Information

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL