Morphological Segmentation with Window LSTM Neural Networks

• DOI: 10.1609/aaai.v30i1.10363
• Publication Date: 2022-06-23T23:51:04Z
• Authors: Linlin Wang; Zhu Cao; Yu Xia; Gerard De Melo
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Morphological segmentation, which aims to break words into meaning-bearing morphemes, is an important task in natural language processing. Most previous work relies heavily on linguistic preprocessing. In this paper, we instead propose novel neural network architectures that learn the structure of input sequences directly from raw and are subsequently able predict morphological boundaries. Our rely Long Short Term Memory (LSTM) units accomplish this, but exploit windows characters capture more contextual information. Experiments multiple languages confirm effectiveness our models task.