{
    "author": null,
    "date_published": null,
    "dek": null,
    "direction": "ltr",
    "domain": "kylrth.com",
    "excerpt": "The B is for bidirectional, and that\u2019s a big deal. It makes it possible to do well on sentence-level (NLI, question answering) and token-level tasks (NER, POS tagging). In a unidirectional model, the…",
    "lead_image_url": null,
    "next_page_url": null,
    "rendered_pages": 1,
    "title": "BERT: pre-training of deep bidirectional transformers for language understanding",
    "total_pages": 1,
    "url": "https://kylrth.com/paper/bert/",
    "word_count": 1
}