Publications

Google Scholar

2024

  1. ACL
    Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses
    Dongxu Zhang, Varun Prashant Gangal, Barrett Martin Lattimer, and Yi Yang
    In Proceedings of the 62th Annual Meeting of the Association for Computational Linguistics 2024

2022

  1. NeurIPS
    Modeling Transitivity and Cyclicity in Directed Graphs via Binary Code Box Embeddings
    Dongxu Zhang, Michael Boratko, Cameron Musco, and Andrew McCallum
    Advances in Neural Information Processing Systems 2022
  2. LREC
    A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes
    Dongxu Zhang*, Sunil Mohan*, Michaela Torkar, and Andrew McCallum
    In Proceedings of the Thirteenth International Conference on Language Resources and Evaluation (LREC) 2022
  3. LREC
    Enhanced Distant Supervision with State-Change Information for Relation Extraction
    Jui Shah*, Dongxu Zhang*, Sam Brody, and Andrew McCallum
    In Proceedings of the Thirteenth International Conference on Language Resources and Evaluation (LREC) 2022
  4. ACL
    Event-Event Relation Extraction using Probabilistic Box Embedding
    EunJeong Hwang, Jay-Yoon Lee, Tianyi Yang, Dhruvesh Patel,  Dongxu Zhang, and Andrew McCallum
    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) 2022

2021

  1. NeurIPS
    Capacity and Bias of Learned Geometric Embeddings for Directed Graphs
    Michael Boratko*, Dongxu Zhang*, Nicholas Monath, Luke Vilnis, Kenneth L. Clarkson, and Andrew McCallum
    Advances in Neural Information Processing Systems 2021

2020

  1. NeurIPS
    Improving local identifiability in probabilistic box embeddings
    Shib Dasgupta*, Michael Boratko*,  Dongxu Zhang, Luke Vilnis, Xiang Li, and Andrew McCallum
    Advances in Neural Information Processing Systems 2020

2019

  1. NAACL
    OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference
    Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Xin Luna Dong, and Andrew McCallum
    In Proceedings of NAACL-HLT 2019
  2. NeurIPS
    Search-guided, lightly-supervised training of structured prediction energy networks
    Amirmohammad Rooshenas,  Dongxu Zhang, Gopal Sharma, and Andrew McCallum
    Advances in Neural Information Processing Systems 2019

2018

  1. Technique Report
    Word embedding perturbation for sentence classification
    Dongxu Zhang, and Zhichao Yang
    arXiv preprint arXiv:1804.08166 2018
  2. ICLR
    Smoothing the geometry of probabilistic box embeddings
    Xiang Li*, Luke Vilnis*,  Dongxu Zhang, Michael Boratko, and Andrew McCallum
    In International Conference on Learning Representations 2018

2017

  1. SIGIR WS
    Pku@ clscisumm-17: Citation contextualization
    Dongxu Zhang, and Sujian Li
    In BIRNDL@ SIGIR (2) 2017

2016

  1. COLING
    Bitext name tagging for cross-lingual entity annotation projection
    Dongxu Zhang, Boliang Zhang, Xiaoman Pan, Xiaocheng Feng, Heng Ji, and Weiran Xu
    In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers 2016
  2. Technique Report
    Learning from LDA using deep neural networks
    Dongxu Zhang, Tianyi Luo, and Dong Wang
    2016

2015

  1. Technique Report
    Relation classification via recurrent neural network
    Dongxu Zhang, and Dong Wang
    arXiv preprint arXiv:1508.01006 2015
  2. ACL WS
    Joint semantic relevance learning with text data and graph knowledge
    Dongxu Zhang, Bin Yuan, Dong Wang, and Rong Liu
    In Proceedings of the 3rd workshop on continuous vector space models and their compositionality 2015