Semantic Scholar Open Access 2022 210 sitasi

A Review on Language Models as Knowledge Bases

Badr AlKhamissi Millicent Li Asli Celikyilmaz Mona T. Diab Marjan Ghazvininejad

Lihat Sumber DOI

Abstrak

Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained on a sufficiently large (web) corpus will encode a significant amount of knowledge implicitly in its parameters. The resulting LM can be probed for different kinds of knowledge and thus acting as a KB. This has a major advantage over traditional KBs in that this method requires no human supervision. In this paper, we present a set of aspects that we deem a LM should have to fully act as a KB, and review the recent literature with respect to those aspects.

Topik & Kata Kunci

Computer Science

Penulis (5)

Badr AlKhamissi

Millicent Li

Asli Celikyilmaz

Mona T. Diab

Marjan Ghazvininejad

Format Sitasi

APA MLA BibTeX

AlKhamissi, B., Li, M., Celikyilmaz, A., Diab, M.T., Ghazvininejad, M. (2022). A Review on Language Models as Knowledge Bases. https://doi.org/10.48550/arXiv.2204.06031

Akses Cepat

Lihat di Sumber doi.org/10.48550/arXiv.2204.06031

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Total Sitasi: 210×
Sumber Database: Semantic Scholar
DOI: 10.48550/arXiv.2204.06031
Akses: Open Access ✓