More than Just Statistical Recurrence: Human and Machine Unsupervised Learning of M\=aori Word Segmentation across Morphological Processes
Varatharaj, Ashvini, Todd, Simon
–arXiv.org Artificial Intelligence
Non-M\=aori-speaking New Zealanders (NMS)are able to segment M\=aori words in a highlysimilar way to fluent speakers (Panther et al.,2024). This ability is assumed to derive through the identification and extraction of statistically recurrent forms. We examine this assumption by asking how NMS segmentations compare to those produced by Morfessor, an unsupervised machine learning model that operates based on statistical recurrence, across words formed by a variety of morphological processes. Both NMS and Morfessor succeed in segmenting words formed by concatenative processes (compounding and affixation without allomorphy), but NMS also succeed for words that invoke templates (reduplication and allomorphy) and other cues to morphological structure, implying that their learning process is sensitive to more than just statistical recurrence.
arXiv.org Artificial Intelligence
Mar-21-2024
- Country:
- Oceania > New Zealand
- North Island
- Waikato (0.04)
- Bay of Plenty Region > Whakatane (0.04)
- Auckland Region > Auckland (0.04)
- North Island
- North America > United States
- Texas (0.04)
- California > Santa Barbara County
- Santa Barbara (0.04)
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Russia > Central Federal District
- Moscow Oblast > Moscow (0.04)
- France > Auvergne-Rhône-Alpes
- Finland > Uusimaa
- Helsinki (0.04)
- United Kingdom > England
- Asia > Middle East
- Jordan (0.04)
- Oceania > New Zealand
- Genre:
- Research Report > New Finding (0.68)