This picture showsXiang Yu

Xiang Yu

Doctoral Researcher
Institute for Natural Language Processing (IMS)
Foundations of Computational Linguistics

Contact

+49 711 685-84583

Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Room: 02.002

2020:

  • Xiang Yu, Simon Tannert, Ngoc Thang Vu and Jonas Kuhn. Fast and Accurate Non-Projective Dependency Tree Linearization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics [paper] [code].
  • Xiang Yu, Ngoc Thang Vu, Jonas Kuhn. Ensemble Self-Training for Low-Resource Languages: Grapheme-to-Phoneme Conversion and Morphological Inflection. In Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology [paper].

2019:

  • Xiang Yu, Agnieszka Falenska, Marina Haid, Ngoc Thang Vu and Jonas Kuhn. IMSurReal: IMS at the Surface Realization Shared Task 2019. In Proceedings of the Second Workshop on Multilingual Surface Realization @EMNLP 2019 [paper] [code].
  • Xiang Yu, Agnieszka Falenska, Ngoc Thang Vu and Jonas Kuhn. Head-First Linearization with Tree-Structured Representation. In Proceedings of the 12th International Conference on Natural Language Generation [code] [paper] (Runner-up for the best paper).
  • Xiang Yu, Agnieszka Falenska and Jonas Kuhn.  Dependency length minimization vs. word order constraints: an empirical study on 55 treebanks. In Proceedings of Quasy 2019  [ paper].
  • Xiang Yu, Ngoc Thang Vu and Jonas Kuhn.  Learning the Dyck Language with Attention-based Seq2Seq Models. In Proceedings of the BlackboxNLP Workshop @ACL 2019  [ paper] [data].

2018:

  • Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu and Ngoc Thang Vu. Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension. In Proceedings of the SIGNLL Conference on Computational Natural Language Learning (CoNLL). Brussels, Belgium, October 2018 [ paper] [ code].
  • Xiang Yu, Ngoc Thang Vu and Jonas Kuhn.  Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning. In Proceedings of the Universal Dependencies Workshop 2018 @EMNLP 2018 [ paper]. 

2017:

  • Xiang Yu, Agnieszka Falenska, and Ngoc Thang Vu, A general-purpose tagger with convolutional neural networksIn Proceedings of  SCLeM workshop @EMNLP 2017 [ paper] [ code].
  • Anders Björkelund, Agnieszka Falenska, Xiang Yu, and Jonas Kuhn,  IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks.   In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) [ paper].
  • Xiang Yu and Ngoc Thang Vu, Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages. In  Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers)  [ paper] [ code].

WS19/20: Statistical Dependency Parsing

WS19/20: Grammar Formalisms and Grammar Engineering (Syntax)

SS19: Parsing

WS18/19: Grammar Formalisms and Grammar Engineering (Syntax)

SS18: Statistical Dependency Parsing

WS17/18: Grammar Formalisms and Grammar Engineering (Grundlagen der Syntax)

SS17: Statistical Dependency Parsing

To the top of the page