CharManteau: Character Embedding Models For Portmanteau Creation

Portmanteaus are a word formation phenomenon where two words are combined to form a new word. We propose character-level neural sequence-to-sequence (S2S) methods for the task of portmanteau generation that are end-to-end-trainable, language independent, and do not explicitly use additional phonetic...

Full description

Saved in:
Bibliographic Details
Main Authors Gangal, Varun, Jhamtani, Harsh, Neubig, Graham, Hovy, Eduard, Nyberg, Eric
Format Journal Article
LanguageEnglish
Published 04.07.2017
Subjects
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary:Portmanteaus are a word formation phenomenon where two words are combined to form a new word. We propose character-level neural sequence-to-sequence (S2S) methods for the task of portmanteau generation that are end-to-end-trainable, language independent, and do not explicitly use additional phonetic information. We propose a noisy-channel-style model, which allows for the incorporation of unsupervised word lists, improving performance over a standard source-to-target model. This model is made possible by an exhaustive candidate generation strategy specifically enabled by the features of the portmanteau task. Experiments find our approach superior to a state-of-the-art FST-based baseline with respect to ground truth accuracy and human evaluation.
DOI:10.48550/arxiv.1707.01176