Fusion of Simple Models for Native Language Identification

@inproceedings{Kepler2017FusionOS,
  title={Fusion of Simple Models for Native Language Identification},
  author={Fabio Kepler and Ram{\'o}n Fern{\'a}ndez Astudillo and Alberto Abad},
  booktitle={BEA@EMNLP},
  year={2017}
}
In this paper we describe the approaches we explored for the 2017 Native Language Identification shared task. We focused on simple word and sub-word units avoiding heavy use of hand-crafted features. Following recent trends, we explored linear and neural networks models to attempt to compensate for the lack of rich feature use. Initial efforts yielded f1-scores of 82.39% and 83.77% in the development and test sets of the fusion track, and were officially submitted to the task as team L2F. After… CONTINUE READING
1 Citations
18 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Native Language Identification: Explorations and Applications

  • Shervin Malmasi.
  • Ph.D. thesis. http://hdl.handle.net/1959.14…
  • 2016
2 Excerpts

Similar Papers

Loading similar papers…