Neural text normalization leveraging similarities of strings and sounds
This work addresses text normalization for natural language processing applications, but it is incremental as it builds on existing neural methods by adding similarity features.
The paper tackled text normalization by proposing neural models that incorporate similarities of word strings and sounds, achieving higher F1 scores than a baseline model.
We propose neural models that can normalize text by considering the similarities of word strings and sounds. We experimentally compared a model that considers the similarities of both word strings and sounds, a model that considers only the similarity of word strings or of sounds, and a model without the similarities as a baseline. Results showed that leveraging the word string similarity succeeded in dealing with misspellings and abbreviations, and taking into account the sound similarity succeeded in dealing with phonetic substitutions and emphasized characters. So that the proposed models achieved higher F$_1$ scores than the baseline.