Abstract
Recent progress in pretraining language models on large corpora has resulted in significant performance gains on many NLP tasks. These large models acquire linguistic knowledge during pretraining, which helps to improve performance on downstream tasks via fine-tuning. To assess what kind of knowledge is acquired, language models are commonly probed by querying them with ‘fill in the blank’ style cloze questions. Existing probing datasets mainly focus on knowledge about relations between words and entities. We introduce WDLMPro (Word Definitions Language Model Probing) to evaluate word understanding directly using dictionary definitions of words. In our experiments, three popular pretrained language models struggle to match words and their definitions. This indicates that they understand many words poorly and that our new probing task is a difficult challenge that could help guide research on LMs in the future.
Dokumententyp: | Konferenzbeitrag (Paper) |
---|---|
EU Funded Grant Agreement Number: | 740516 |
EU-Projekte: | Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement |
Fakultätsübergreifende Einrichtungen: | Centrum für Informations- und Sprachverarbeitung (CIS) |
Themengebiete: | 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme
400 Sprache > 400 Sprache 400 Sprache > 410 Linguistik |
URN: | urn:nbn:de:bvb:19-epub-92191-7 |
Ort: | Stroudsburg, PA |
Sprache: | Englisch |
Dokumenten ID: | 92191 |
Datum der Veröffentlichung auf Open Access LMU: | 27. Mai 2022, 08:55 |
Letzte Änderungen: | 27. Mai 2022, 08:55 |