CharManteau: Character Embedding Models For Portmanteau Creation
This work addresses a niche linguistic task for natural language processing applications, with incremental improvements over existing methods.
The authors tackled the problem of generating portmanteaus (combined words) by proposing character-level neural sequence-to-sequence methods, which outperformed a state-of-the-art baseline in ground truth accuracy and human evaluation.
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.