Feedforward Approach to Sequential Morphological Analysis in the Tagalog Language

Morphological analysis is a preprocessing task used to normalize and get the grammatical information of a word which may also be referred to as lemmatization. Several NLP tasks use this preprocessing technique to improve their implementations in different languages, however languages like Tagalog, are considered to be morphosyntactically rich for having a diverse number of morphological phenomena. This paper presents a Tagalog morphological analyzer implemented using a Feed Forward Neural Networks model (FFNN). We transformed our data to its character-level representation and used the model to identify its capability of learning the language's inflections. We compared our MA to previous rule-based Tagalog MA works and saw an improved accuracy of 0.93.