@inproceedings{sorodoc-etal-2021-controlled,
    title = "Controlled tasks for model analysis: Retrieving discrete information from sequences",
    author = "Sorodoc, Ionut-Teodor  and
      Boleda, Gemma  and
      Baroni, Marco",
    editor = "Bastings, Jasmijn  and
      Belinkov, Yonatan  and
      Dupoux, Emmanuel  and
      Giulianelli, Mario  and
      Hupkes, Dieuwke  and
      Pinter, Yuval  and
      Sajjad, Hassan",
    booktitle = "Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2021.blackboxnlp-1.37/",
    doi = "10.18653/v1/2021.blackboxnlp-1.37",
    pages = "468--478",
    abstract = "In recent years, the NLP community has shown increasing interest in analysing how deep learning models work. Given that large models trained on complex tasks are difficult to inspect, some of this work has focused on controlled tasks that emulate specific aspects of language. We propose a new set of such controlled tasks to explore a crucial aspect of natural language processing that has not received enough attention: the need to retrieve discrete information from sequences. We also study model behavior on the tasks with simple instantiations of Transformers and LSTMs. Our results highlight the beneficial role of decoder attention and its sometimes unexpected interaction with other components. Moreover, we show that, for most of the tasks, these simple models still show significant difficulties. We hope that the community will take up the analysis possibilities that our tasks afford, and that a clearer understanding of model behavior on the tasks will lead to better and more transparent models."
}