Multi-Sense Language Modelling
release_uohwpw4fubgapgystba3vbelnu
by
Andrea Lekkas, Peter Schneider-Kamp, Isabelle Augenstein
2020
Abstract
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.
In text/plain
format
Archived Files and Locations
application/pdf 463.2 kB
file_ohjcar4kprgjzo36nsw2zqjyji
|
arxiv.org (repository) web.archive.org (webarchive) |
2012.05776v1
access all versions, variants, and formats of this works (eg, pre-prints)