@inproceedings{kang-etal-2022-kala,
    title = "{KALA:} Knowledge-Augmented Language Model Adaptation",
    author = "Kang, Minki  and
      Baek, Jinheon  and
      Hwang, Sung Ju",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.379",
    doi = "10.18653/v1/2022.naacl-main.379",
    pages = "5144--5167",
    abstract = "Pre-trained language models (PLMs) have achieved remarkable success on various natural language understanding tasks. Simple fine-tuning of PLMs, on the other hand, might be suboptimal for domain-specific tasks because they cannot possibly cover knowledge from all domains. While adaptive pre-training of PLMs can help them obtain domain-specific knowledge, it requires a large training cost. Moreover, adaptive pre-training can harm the PLM{'}s performance on the downstream task by causing catastrophic forgetting of its general knowledge. To overcome such limitations of adaptive pre-training for PLM adaption, we propose a novel domain adaption framework for PLMs coined as Knowledge-Augmented Language model Adaptation (KALA), which modulates the intermediate hidden representations of PLMs with domain knowledge, consisting of entities and their relational facts. We validate the performance of our KALA on question answering and named entity recognition tasks on multiple datasets across various domains. The results show that, despite being computationally efficient, our KALA largely outperforms adaptive pre-training.",
}