TY - JOUR AU - van der Goot, Rob AU - van Noord, Gertjan PY - 2017/12/01 Y2 - 2024/03/28 TI - MoNoise: Modeling Noise Using a Modular Normalization System JF - Computational Linguistics in the Netherlands Journal JA - CLIN Journal VL - 7 IS - 0 SE - Articles DO - UR - https://www.clinjournal.org/clinj/article/view/74 SP - 129-144 AB - <p>We propose MoNoise: a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable. Normalization is the task of translating texts from a noncanonical domain to a more canonical domain, in our case: from social media data to standard language. Our proposed model is based on a modular candidate generation in which each module is responsible for a different type of normalization action. The most important generation modules are a spelling correction system and a word embeddings module. Depending on the definition of the normalization task, a static lookup list can be crucial for performance. We train a random forest classifier to rank the candidates, which generalizes well to all different types of normalization actions. Most features for the ranking originate from the generation modules; besides these features, N-gram features prove to be an important source of information. We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.</p> ER -