Year: 2019
Type: conference-paper
Abstract: Our submission to the MADAR shared task on Arabic dialect identification (Bouamor et al., 2019) employed a language modeling technique called Prediction by Partial Matching, an ensemble of neural architectures, and sources of additional data for training word embeddings and auxiliary language models. 1 We found several of these techniques provided small boosts in performance, though a simple character-level language model was a strong baseline, and a lower-order LM achieved best performance on Subtask 2. Interestingly, word embeddings provided no consistent benefit, and ensembling struggled to outperform the best component submodel.This suggests the variety of architectures are learning redundant information, and future work may focus on encouraging decorrelated learning.
DOI: 10.18653/v1/w19-4634
Institution: Johns Hopkins University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2971130934