NEMO: Frequentist Inference Approach to Constrained Linguistic Typology Feature Prediction in SIGTYP 2020 Shared Task
This work addresses a domain-specific challenge in computational linguistics for predicting language features, but it is incremental as it builds on existing methods and shared task frameworks.
The paper tackled the problem of predicting linguistic typological features for multiple languages using data from the World Atlas of Language Structures, achieving a micro-averaged accuracy of 0.66 on 149 test languages with their best configuration.
This paper describes the NEMO submission to SIGTYP 2020 shared task which deals with prediction of linguistic typological features for multiple languages using the data derived from World Atlas of Language Structures (WALS). We employ frequentist inference to represent correlations between typological features and use this representation to train simple multi-class estimators that predict individual features. We describe two submitted ridge regression-based configurations which ranked second and third overall in the constrained task. Our best configuration achieved the micro-averaged accuracy score of 0.66 on 149 test languages.