Google Scholar profile

2024

  • Socratic Reasoning Improves Positive Text Rewriting
    Anmol Goel, Nico Daheim, Iryna Gurevych
    preprint [pdf]
    *Equal contribution.

  • Variational Learning is Effective for Large Deep Networks
    Yuesong Shen*, Nico Daheim*, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff
    preprint [pdf] [Code]

  • Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
    Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti
    NAACL 2024 [pdf] [code]

  • Model Merging by Uncertainty-Based Gradient Matching
    Nico Daheim, Thomas Möllenhoff, Edoardo M. Ponti, Iryna Gurevych, Mohammad Emtiyaz Khan
    ICLR 2024 [pdf]

2023

  • Uncertainty in Natural Language Generation: From Theory to Applications
    Joris Baan*, Nico Daheim*, Evgenia Ilia*, Dennis Ulmer*, Haau-Sing Li, Raquel Fernández, Barbara Plank, Rico Sennrich, Chrysoula Zerva, Wilker Aziz
    preprint [pdf]
    *Equal contribution.

  • Opportunities and Challenges in Neural Dialog Tutoring
    Jakub Macina*, Nico Daheim*, Sankalan Pal Chowdhury*, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
    EMNLP Findings 2023 [pdf] [Code & data]
    *Equal contribution.

  • Task-Oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10
    David Thulke, Nico Daheim, Christian Dugast, Hermann Ney
    IEEE/ACM Transactions on Audio, Speech, and Language Processing [pdf]

  • Opportunities and Challenges in Neural Dialog Tutoring
    Jakub Macina*, Nico Daheim*, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
    EACL 2023 [pdf]
    *Equal contribution.

  • Poor Man’s Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
    Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan
    EACL 2023 [pdf]

2022

  • Controllable Factuality in Document-Grounded Dialog Using a Noisy Channel Model
    Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
    EMNLP Findings 2022 [pdf] [code]

  • Gemv2: Multilingual nlg benchmarking in a single line of code
    Sebastian Gehrmann et al.
    EMNLP Demo 2022 [pdf] [code]

  • Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model
    David Thulke*, Nico Daheim*, Christian Dugast, Hermann Ney
    Workshop on DSTC10, AAAI 2022 [pdf] [code]
    *Equal contribution.

2021

  • Cascaded Span Extraction and Response Generation for Document-Grounded Dialog
    Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
    Workshop on DialDoc, ACL-IJCNLP 2021 [pdf] [code]

  • Efficient Retrieval Augmented Generation from Unstructed Knowledge for Task-Oriented Dialog Recognition
    David Thulke, Nico Daheim, Christian Dugast, Hermann Ney
    Workshop on DSTC9, AAAI 2021 [pdf] [code]