Edinburgh Research Explorer
  1. 2017
  2. From characters to words to in between: Do we capture morphology?

    Vania, C. & Lopez, A., 4 Aug 2017, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) . Association for Computational Linguistics, p. 2016-2027 12 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. UParse: the Edinburgh system for the CoNLL 2017 UD shared task

    Vania, C., Zhang, X. & Lopez, A., 4 Aug 2017, Proceedings of the Conference on Computational Natural Language Learning Shared Task (CoNLL 17). Association for Computational Linguistics (ACL), p. 100-110 11 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  4. 2018
  5. Explicitly modeling case improves neural dependency parsing

    Vania, C. & Lopez, A., Nov 2018, Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP . Brussels, Belgium : ACL Anthology, p. 356-358 3 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  6. What do character-level models learn about morphology? The case of dependency parsing

    Vania, C., Grivas, A. & Lopez, A., 1 Nov 2018, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium : Association for Computational Linguistics, p. 2573-2583 11 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  7. 2019
  8. A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages

    Vania, C., Kementchedjhieva, Y., Søgaard, A. & Lopez, A., 4 Nov 2019, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing. Association for Computational Linguistics, p. 1105–1116 13 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution