
Abstract
When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big models, resulting in a large carbon footprint and making it difficult for researchers and practitioners to use them. We show that performance similar to GPT-3 can be obtained with language models that are much “greener” in that their parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that contain a task description, combined with gradient-based optimization; exploiting unlabeled data gives further improvements. We identify key factors required for successful natural language understanding with small language models.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
EU Funded Grant Agreement Number: | 740516 |
EU Projects: | Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement |
Research Centers: | Center for Information and Language Processing (CIS) |
Subjects: | 000 Computer science, information and general works > 000 Computer science, knowledge, and systems 400 Language > 400 Language 400 Language > 410 Linguistics |
URN: | urn:nbn:de:bvb:19-epub-92198-7 |
Place of Publication: | Stroudsburg, PA |
Language: | English |
Item ID: | 92198 |
Date Deposited: | 27. May 2022, 09:53 |
Last Modified: | 27. May 2022, 09:53 |