A two-step convolutional neural network approach for semantic role labeling

@article{Fonseca2013ATC,
  title={A two-step convolutional neural network approach for semantic role labeling},
  author={Erick Rocha Fonseca and Jo{\~a}o Lu{\'i}s Garcia Rosa},
  journal={The 2013 International Joint Conference on Neural Networks (IJCNN)},
  year={2013},
  pages={1-7}
}
Semantic role labeling (SRL) is a well known task in Natural Language Processing, consisting of identifying and labeling verbal arguments. It has been widely studied in English, but scarcely explored in other languages. In this paper, we employ a two-step convolutional neural architecture to label semantic arguments in Brazilian Portuguese texts, and avoid the use of external NLP tools. We achieve an F1 score of 62.2, which, although considerably lower than the state-of-the-art for English… CONTINUE READING
Highly Cited
This paper has 19 citations. REVIEW CITATIONS
13 Citations
20 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 13 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 20 references

Anotação automática semissupervisionada de papéis semânticos para o português do Brasil

  • F. E. Alva Manchego
  • Master’s dissertation, Instituto de Ciências…
  • 2013
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…