Charles Explorer logo
🇨🇿

CUNI Submission to MRL 2023 Shared Task on Multi-lingual Multi-task Information Retrieval

Publikace na Matematicko-fyzikální fakulta |
2023

Tento text není v aktuálním jazyce dostupný. Zobrazuje se verze "en".Abstrakt

We present the Charles University system for the MRL 2023 Shared Task on Multi-lingual Multi-task Information Retrieval.

The goal of the shared task was to develop systems for named entity recognition and question answering in several under-represented languages.

Our solutions to both subtasks rely on the translate-test approach.

We first translate the unlabeled examples into English using a multilingual machine translation model.

Then, we run inference on the translated data using a strong task-specific model.

Finally, we project the labeled data back into the original language.

To keep the inferred tags on the correct positions in the original language, we propose a method based on scoring the candidate positions using a label-sensitive translation model.

In both settings, we experiment with finetuning the classification models on the translated data.

However, due to a domain mismatch between the development data and the shared task validation and test sets, the finetuned models could not outperform our baselines.