Patrick Huber

Welcome to my Website!

I am a third year Ph.D. candidate in the NLP Lab at the University of British Columbia.

I am interested in innovative applications of machine learning methods and algorithms, focusing on designing and implementing computational models that enable automated systems to better understand natural language.

  • News
  • About
  • Awards
  • Publications
  • Resume
  • Reviewing
  • Talks
  • Publications


    2022

    • Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation
      Huber, Patrick and Xing, Linzi and Carenini, Giuseppe
      [PDF]
    2021

    • Unsupervised Learning of Discourse Structures using a Tree Autoencoder
      Huber, Patrick and Carenini, Giuseppe
      [PDF]
    • Predicting Discourse Trees from Transformer-based Neural Summarizers
      Xiao, Wen and Huber, Patrick and Carenini, Giuseppe
      [PDF]
    • W-RST: Towards a Weighted RST-style Discourse Framework
      Huber, Patrick and Xiao, Wen and Carenini, Giuseppe
      Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
      [PDF]
    • CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training
      Huber, Patrick and Aghajanyan, Armen and Oğuz, Barlas and Okhonko, Dmytro and Yih, Wen-tau and Gupta, Sonal and Chen, Xilun
      [PDF]
    2020

    • Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help!
      Xiao, Wen and Huber, Patrick and Carenini, Giuseppe
      Proceedings of the First Workshop on Computational Approaches to Discourse (CODI)
      [PDF]
    • MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision
      Huber, Patrick and Carenini, Giuseppe
      Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
      [PDF]
    • From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation
      Huber, Patrick and Carenini, Giuseppe
      The 28th International Conference on Computational Linguisics (COLING)
      [PDF]
    • Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining
      Guz, Grigorii and Huber, Patrick and Carenini, Giuseppe
      The 28th International Conference on Computational Linguisics (COLING)
      [PDF]
    2019

    • Predicting Discourse Structure using Distant Supervision from Sentiment
      Huber, Patrick and Carenini, Giuseppe
      Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
      [PDF]
    2018

    • Automated Evaluation of Out-of-Context Errors
      Huber, Patrick and Niehues, Jan and Waibel, Alex
      Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
      [PDF]
    2017

    • A Hierarchical Approach to Neural Context-Aware Modeling
      Huber, Patrick
      Master Thesis
      [PDF]