LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations

@article{Eichler2019LINSPECTORWA,
  title={LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations},
  author={Max Eichler and G{\"o}zde G{\"u}l Sahin and Iryna Gurevych},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.11438}
}
We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations. Our system provides researchers working in low-resource settings with an easily accessible web based probing tool to gain quick insights into their word embeddings especially outside of the English language. To do this we employ 16 simple linguistic probing tasks such as gender, case marking, and tense for a diverse set of 28 languages. We support probing of static word embeddings along with… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Automatic differentiation in PyTorch

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Enhanced LSTM for Natural Language Inference

  • ACL
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Analysis Methods in Neural Language Processing: A Survey

  • Transactions of the Association for Computational Linguistics
  • 2018

Proceedings of the 2018 emnlp workshop blackboxnlp: Analyzing and interpreting neural networks for nlp

Tal Linzen, Grzegorz Chrupała, Afra Alishahi.
  • Association for Computational Linguistics.
  • 2018
VIEW 1 EXCERPT