Multi-Sense Language Modelling
This work tackles the challenging problem of explicitly modeling polysemy in language models, which could benefit end tasks like assistive writing and improve linking language models with knowledge bases.
The paper proposes a multi-sense language model that predicts both the next word and its sense in context, aiming to address the current lack of explicit polysemy modeling in common language models. It introduces a structured prediction framework that decomposes the task into word and sense prediction, utilizing a Graph Attention Network to encode sense definitions and examples.
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. To aid 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.