@inproceedings{anuranjana-2023-discoflan,
    title = "{D}isco{F}lan: Instruction Fine-tuning and Refined Text Generation for Discourse Relation Label Classification",
    author = "Anuranjana, Kaveri",
    editor = "Braud, Chlo{\'e}  and
      Liu, Yang Janet  and
      Metheniti, Eleni  and
      Muller, Philippe  and
      Rivi{\`e}re, Laura  and
      Rutherford, Attapol  and
      Zeldes, Amir",
    booktitle = "Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.disrpt-1.2/",
    doi = "10.18653/v1/2023.disrpt-1.2",
    pages = "22--28",
    abstract = "This paper introduces DiscoFlan, a multilingual discourse relation classifier submitted for DISRPT 2023. Our submission represents the first attempt at building a multilingual discourse relation classifier for the DISRPT 2023 shared task. By our model addresses the issue to mismatches caused by hallucination in a seq2seq model by utilizing the label distribution information for label generation. In contrast to the previous state-of-the-art model, our approach eliminates the need for hand-crafted features in computing the discourse relation classes. Furthermore, we propose a novel label generation mechanism that anchors the labels to a fixed set by selectively enhancing training on the decoder model. Our experimental results demonstrate that our model surpasses the current state-of-the-art performance in 11 out of the 26 datasets considered, however the submitted model compatible with provided evaluation scripts is better in 7 out of 26 considered datasets, while demonstrating competitive results in the rest. Overall, DiscoFlan showcases promising advancements in multilingual discourse relation classification for the DISRPT 2023 shared task."
}