An improved Bayesian TRIE based model for SMS text normalization

TL;DR

This paper introduces an improved Bayesian Trie model for SMS text normalization, enhancing probability estimation and integrating it into error correction, resulting in better performance over previous methods.

Contribution

It proposes a structural modification, a novel training algorithm, and probability generation scheme for Trie-based SMS normalization, with proven statistical properties and improved accuracy.

Findings

Proposed Trie model is an unbiased, consistent estimator of word probabilities.

Fusion into noisy channel error correction improves normalization accuracy.

Simulation results show superiority over previous approaches.

Abstract

Normalization of SMS text, commonly known as texting language, is being pursued for more than a decade. A probabilistic approach based on the Trie data structure was proposed in literature which was found to be better performing than HMM based approaches proposed earlier in predicting the correct alternative for an out-of-lexicon word. However, success of the Trie based approach depends largely on how correctly the underlying probabilities of word occurrences are estimated. In this work we propose a structural modification to the existing Trie-based model along with a novel training algorithm and probability generation scheme. We prove two theorems on statistical properties of the proposed Trie and use them to claim that is an unbiased and consistent estimator of the occurrence probabilities of the words. We further fuse our model into the paradigm of noisy channel based error correction and provide a heuristic to go beyond a Damerau Levenshtein distance of one. We also run simulations to support our claims and show superiority of the proposed scheme over previous works.