Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples

@inproceedings{Joshi2018ExtendingAP,
  title={Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples},
  author={Vidur Joshi and Matthew Peters and Mark Hopkins},
  booktitle={ACL},
  year={2018}
}
We revisit domain adaptation for parsers in the neural era. First we show that recent advances in word representations greatly diminish the need for domain adaptation when the target domain is syntactically similar to the source domain. As evidence, we train a parser on the Wall Street Jour- nal alone that achieves over 90% F1 on the Brown corpus. For more syntactically dis- tant domains, we provide a simple way to adapt a parser using only dozens of partial annotations. For instance, we… CONTINUE READING
5
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • As evidence, we train a parser on the Wall Street Jour- nal alone that achieves over 90% F1 on the Brown corpus.
  • In the process, we demon- strate a new state-of-the-art single model result on the Wall Street Journal test set of 94.3%.
  • We raise the state-of-the-art single-model F1score for constituency parsing from 92.6% to 94.3% on the Wall Street Journal (WSJ) test set.

References

Publications referenced by this paper.
SHOWING 1-10 OF 49 REFERENCES