CLJul 4, 2017

CharManteau: Character Embedding Models For Portmanteau Creation

arXiv:1707.01176v21093 citations
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes