@inproceedings{al-negheimish-etal-2023-towards,
    title = "Towards preserving word order importance through Forced Invalidation",
    author = "Al-Negheimish, Hadeel  and
      Madhyastha, Pranava  and
      Russo, Alessandra",
    editor = "Vlachos, Andreas  and
      Augenstein, Isabelle",
    booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.eacl-main.187/",
    doi = "10.18653/v1/2023.eacl-main.187",
    pages = "2563--2570",
    abstract = "Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks. However, recent findings have revealed that pre-trained language models are insensitive to word order. The performance on NLU tasks remains unchanged even after randomly permuting the word of a sentence, where crucial syntactic information is destroyed. To help preserve the importance of word order, we propose a simple approach called Forced Invalidation (FI): forcing the model to identify permuted sequences as invalid samples. We perform an extensive evaluation of our approach on various English NLU and QA based tasks over BERT-based and attention-based models over word embeddings. Our experiments demonstrate that FI significantly improves the sensitivity of the models to word order."
}