LaBSE
Related Papers
IIT Bombay’s WMT22 Automatic Post-Editing Shared Task Submission
AbstractThis paper describes IIT Bombay’s submission to the WMT22 Automatic Post-Editing (APE) shared task for the English-Marathi (En-Mr) language pair. We follow the curriculum training strategy to train our APE …...
Manifold’s English-Chinese System at WMT22 General MT Task
AbstractManifold’s English-Chinese System at WMT22 is an ensemble of 4 models trained by different configurations with scheduled sampling-based fine-tuning. The four configurations are DeepBig (XenC), DeepLarger (XenC), DeepBig-TalkingHeads (XenC) and …...
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?
AbstractDense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art resultsin various tasks requiring semantic …...
Multilingual Representation Distillation with Contrastive Learning
AbstractMultilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we …...
Probing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders
AbstractPretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear …...
Target Language Monolingual Translation Memory based NMT by Cross-lingual Retrieval of Similar Translations and Reranking
AbstractRetrieve-edit-rerank is a text generation framework composed of three steps: retrieving for sentences using the input sentence as a query, generating multiple output sentence candidates, and selecting the final output …...