Cross-Lingual Natural Language Inference
17 papers with code • 1 benchmarks • 2 datasets
Using data and models available for one language for which ample such resources are available (e.g., English) to solve a natural language inference task in another, commonly more low-resource, language.
LibrariesUse these libraries to find Cross-Lingual Natural Language Inference models and implementations
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features.
We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts.
Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods.
We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models.
While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual embeddings define a multilingual space where word embeddings from two or more languages are integrated together.
Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora, and do not make use of the strong cross-lingual signal contained in parallel data.