Files

Abstract

Neural language models typically employ a categorical approach to prediction and training, leading to several well-known computational and numerical limitations. These limitations are particularly evident in applied settings where language models are employed as means for communication. From speller systems employed as assistive technology to texting applications on smartphones, all language models revolve around category-based prediction. Research shows that neural-category approaches to language modeling are questionable for predicting low-frequency words that are essential for user personalization. It is also challenging to adapt these architectures to a changing vocabulary due to the initially learned vocabulary constraints, which limit predictions of relevant categories (i.e., words) a user can type. Recently, such categorical models were shown to be relatively complex with long inference times, which may be detrimental for user engagement. In this thesis, I reevaluate neural-category approaches and propose an alternative: continuous output prediction.

Details

PDF

Statistics

from
to
Export
Download Full History