Multi-Sense Language Modelling
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning
Dokumenter
- Multi-Sense Language Modelling
Forlagets udgivne version, 408 KB, PDF-dokument
The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language modelling architectures explicitly model polysemy. We propose a language model which not only predicts the next word, but also its sense in context. We argue that this higher prediction granularity may be useful for end tasks such as assistive writing, and allow for more a precise linking of language models with knowledge bases. We find that multi-sense language modelling requires architectures that go beyond standard language models, and here propose a structured prediction framework that decomposes the task into a word followed by a sense prediction task. For sense prediction, we utilise a Graph Attention Network, which encodes definitions and example uses of word senses. Overall, we find that multi-sense language modelling is a highly challenging task, and suggest that future work focus on the creation of more annotated training datasets.
Originalsprog | Engelsk |
---|---|
Tidsskrift | arXiv |
Vol/bind | CyRR 2020 |
Antal sider | 10 |
DOI | |
Status | Udgivet - 2020 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 254783161