Neural and Linear Pipeline Approaches to Cross-lingual Morphological Analysis

Abstract

This paper describes Tübingen-Oslo team's participation in the cross-lingual morphological analysis task in the VarDial 2019 evaluation campaign. We participated in the shared task with a standard neural network model. Our model achieved analysis F1-scores of 31.48 and 23.67 on test languages Karachay-Balkar (Turkic) and Sardinian (Romance) respectively. The scores are comparable to the scores obtained by the other participants in both language families, and the analysis score on the Romance data set was also the best result obtained in the shared task. Besides describing the system used in our shared task participation, we describe another, simpler, model based on linear classifiers, and present further analyses using both models. Our analyses, besides revealing some of the difficult cases, also confirm that the usefulness of a source language in this task is highly correlated with the similarity of source and target languages.

Cross-lingual morphological inflection with explicit alignment

“…As a result, we report below some of the experiments with transliterations between Latin and Cyrillic scripts for only eight language pairs (all Turkic languages) to demonstrate the potential gains that can be obtained with transliteration. The transliteration method follows Çöltekin and Barnes (2019). The method does not follow any transliteration standards (e.g., one set by ISO), but tries to maximize the similarities of the writing traditions in these particular languages.…”