BibTeX

@InProceedings{bjorkelund-EtAl:2017:K17-3,
  author = {Bj{o}rkelund, Anders  and  Falenska, Agnieszka  and  Yu, Xiang  and  Kuhn, Jonas},
  title     = {IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks},
  booktitle = {Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies},
  month     = {August},
  year      = 2017,
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {40-51},
  abstract  = {This paper presents the IMS contribution to the CoNLL 2017 Shared Task. In the
	preprocessing step we employed a CRF POS/morphological tagger and a neural
	tagger predicting supertags. On some languages, we also applied word
	segmentation with the CRF tagger and sentence segmentation with a
	perceptron-based parser. For parsing we took an ensemble approach by blending
	multiple instances of three parsers with very different architectures. Our
	system achieved the third place overall and the second place for the surprise
	languages.},
  url       = {https://www.aclweb.org/anthology/K17-3004}
}

@InProceedings{blohm-etal-2018-comparing,
    title = "Comparing Attention-Based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension",
  author = "Blohm, Matthias  and
      Jagfeld, Glorianna  and
      Sood, Ekta  and
      Yu, Xiang  and
      Vu, Ngoc Thang",
    booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/K18-1011",
    doi = "10.18653/v1/K18-1011",
    pages = "108-118",
    abstract = "We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the limitations of our model as well as the behavioral difference between convolutional and recurrent neural networks, we generate adversarial examples to confuse the model and compare to human performance. Furthermore, we assess the generalizability of our model by analyzing its differences to human inference, drawing upon insights from cognitive science.",
}

@InProceedings{yu-etal-2019-imsurreal,
    title = {{{IMS}ur{R}eal: {IMS} at the Surface Realization Shared Task 2019}},
  author = "Yu, Xiang  and
      Falenska, Agnieszka  and
      Haid, Marina  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the 2nd Workshop on Multilingual Surface Realisation (MSR 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-6306",
    doi = "10.18653/v1/D19-6306",
    pages = "50-58",
}

@InProceedings{yu-etal-2019-dependency,
    title = "Dependency Length Minimization vs. Word Order Constraints: An Empirical Study On 55 Treebanks",
  author = "Yu, Xiang  and
      Falenska, Agnieszka  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the First Workshop on Quantitative Syntax (Quasy, SyntaxFest 2019)",
    month = "26 " # aug,
    year = "2019",
    address = "Paris, France",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W19-7911",
    pages = "89-97",
}

@InProceedings{yu-falenska-vu:2017:SCLeM,
  author = {Yu, Xiang  and  Falenska, Agnieszka  and  Vu, Ngoc Thang},
  title     = {A General-Purpose Tagger with Convolutional Neural Networks},
  booktitle = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
  month     = {September},
  year      = 2017,
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {124-129},
  abstract  = {We present a general-purpose tagger based on convolutional neural networks
	(CNN), used for both composing word vectors and encoding context information.
	The CNN tagger is robust across different tagging tasks: without task-specific
	tuning of hyper-parameters, it achieves state-of-the-art results in
	part-of-speech tagging, morphological tagging and supertagging. The CNN tagger
	is also robust against the out-of-vocabulary problem; it performs well on
	artificially unnormalized texts.},
  url       = {https://www.aclweb.org/anthology/W17-4118}
}

@InProceedings{yu-etal-2019-head,
    title = {{Head-First Linearization with Tree-Structured Representation}},
  author = "Yu, Xiang  and
      Falenska, Agnieszka  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
    month = oct # " - " # nov,
    year = "2019",
    address = "Tokyo, Japan",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W19-8636",
    pages = "279-289",
}

@InProceedings{yu-etal-2020-fast,
    title = "Fast and Accurate Non-Projective Dependency Tree Linearization",
  author = "Yu, Xiang  and
      Tannert, Simon  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.134",
    doi = "10.18653/v1/2020.acl-main.134",
    pages = "1451-1462",
    abstract = "We propose a graph-based method to tackle the dependency tree linearization task. We formulate the task as a Traveling Salesman Problem (TSP), and use a biaffine attention model to calculate the edge costs. We facilitate the decoding by solving the TSP for each subtree and combining the solution into a projective tree. We then design a transition system as post-processing, inspired by non-projective transition-based parsing, to obtain non-projective sentences. Our proposed method outperforms the state-of-the-art linearizer while being 10 times faster in training and decoding.",
}

@InProceedings{yu-vu:2017:ACL,
  title={Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages},
  author = {Yu, Xiang and Vu, Ngoc Thang},
  booktitle={Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  volume={2},
  pages={672-678},
  year={2017}
}

@InProceedings{yu-etal-2018-approximate,
    title = "Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning",
  author = "Yu, Xiang  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the Second Workshop on Universal Dependencies ({UDW} 2018)",
    month = nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W18-6021",
    doi = "10.18653/v1/W18-6021",
    pages = "183-191",
    abstract = "We present a general approach with reinforcement learning (RL) to approximate dynamic oracles for transition systems where exact dynamic oracles are difficult to derive. We treat oracle parsing as a reinforcement learning problem, design the reward function inspired by the classical dynamic oracle, and use Deep Q-Learning (DQN) techniques to train the oracle with gold trees as features. The combination of a priori knowledge and data-driven methods enables an efficient dynamic oracle, which improves the parser performance over static oracles in several transition systems.",
}

@InProceedings{yu-etal-2019-learning,
    title = "Learning the {D}yck Language with Attention-based {S}eq2{S}eq Models",
  author = "Yu, Xiang  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W19-4815",
    doi = "10.18653/v1/W19-4815",
    pages = "138-146",
}

@InProceedings{yu-etal-2020-ensemble,
    title = "Ensemble Self-Training for Low-Resource Languages: Grapheme-to-Phoneme Conversion and Morphological Inflection",
  author = "Yu, Xiang  and
      Vu, Ngoc Thang  and
      Kuhn, Jonas",
    booktitle = "Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.sigmorphon-1.5",
    doi = "10.18653/v1/2020.sigmorphon-1.5",
    pages = "70-78",
    abstract = "We present an iterative data augmentation framework, which trains and searches for an optimal ensemble and simultaneously annotates new training data in a self-training style. We apply this framework on two SIGMORPHON 2020 shared tasks: grapheme-to-phoneme conversion and morphological inflection. With very simple base models in the ensemble, we rank the first and the fourth in these two tasks. We show in the analysis that our system works especially well on low-resource languages.",
}