Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task
This work addresses quality estimation for machine translation, specifically for English-German, but is incremental as it builds on existing frameworks and methods.
The paper tackled the WMT2023 Quality Estimation shared task by generating pseudo MQM data from parallel translation data and pre-training an XLMR large model, then fine-tuning it on real data, achieving the best results for English-German in both word-level and fine-grained error span detection sub-tasks by a considerable margin.
We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn sentence-level scores and word-level tags. Empirically, we conduct experiments to find the key hyper-parameters that improve the performance. Technically, we propose a simple method that covert the word-level outputs to fine-grained error span results. Overall, our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks by a considerable margin.