Transquest At WMT2020: Sentence-level Direct Assessment | Awesome LLM Papers Add your paper to Awesome LLM Papers

Transquest At WMT2020: Sentence-level Direct Assessment

Tharindu Ranasinghe, Constantin Orasan, Ruslan Mitkov . Proceedings of the 28th International Conference on Computational Linguistics 2020 – 67 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Coling Image Text Integration Interdisciplinary Approaches Multimodal Semantic Representation Tools Visual Contextualization

This paper presents the team TransQuest’s participation in Sentence-Level Direct Assessment shared task in WMT 2020. We introduce a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. The proposed methods achieve state-of-the-art results surpassing the results obtained by OpenKiwi, the baseline used in the shared task. We further fine tune the QE framework by performing ensemble and data augmentation. Our approach is the winning solution in all of the language pairs according to the WMT 2020 official results.

Similar Work