@inproceedings{chua-etal-2022-unified,
    title = "A unified framework for cross-domain and cross-task learning of mental health conditions",
    author = "Chua, Huikai  and
      Caines, Andrew  and
      Yannakoudakis, Helen",
    editor = "Biester, Laura  and
      Demszky, Dorottya  and
      Jin, Zhijing  and
      Sachan, Mrinmaya  and
      Tetreault, Joel  and
      Wilson, Steven  and
      Xiao, Lu  and
      Zhao, Jieyu",
    booktitle = "Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.nlp4pi-1.1",
    doi = "10.18653/v1/2022.nlp4pi-1.1",
    pages = "1--14",
    abstract = "The detection of mental health conditions based on an individual{'}s use of language has received considerable attention in the NLP community. However, most work has focused on single-task and single-domain models, limiting the semantic space that they are able to cover and risking significant cross-domain loss. In this paper, we present two approaches towards a unified framework for cross-domain and cross-task learning for the detection of depression, post-traumatic stress disorder and suicide risk across different platforms that further utilizes inductive biases across tasks. Firstly, we develop a lightweight model using a general set of features that sets a new state of the art on several tasks while matching the performance of more complex task- and domain-specific systems on others. We also propose a multi-task approach and further extend our framework to explicitly capture the affective characteristics of someone{'}s language, further consolidating transfer of inductive biases and of shared linguistic characteristics. Finally, we present a novel dynamically adaptive loss weighting approach that allows for more stable learning across imbalanced datasets and better neural generalization performance. Our results demonstrate the effectiveness of our unified framework for mental ill-health detection across a number of diverse English datasets.",
}