cross-lingual

Multilingual Voice Understanding Model

“百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型，具有优越的英语/中文能力，在多语言和通用任务等多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction.

Text2Text Language Modeling Toolkit

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

Multilingual sentence alignment using sentence embeddings

Cross-Lingual Alignment of Contextual Word Embeddings

XPersona: Evaluating Multilingual Personalized Chatbot

Cross-Lingual Machine Reading Comprehension (EMNLP 2019)

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask prompting.

A Multi-subject High School Examinations Dataset for Cross-lingual and Multilingual Question Answering