Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are...
Transfer learning has recently become the dominant paradigm of machine
l...
Multilingual task-oriented dialogue (ToD) facilitates access to services...
Fine-tuning all parameters of a pre-trained model has become the mainstr...
Can we construct a neural model that is inductively biased towards learn...
While achieving state-of-the-art results in multiple tasks and languages...
Model-agnostic meta-learning (MAML) has been recently put forth as a str...
The goal of generative phonology, as formulated by Chomsky and Halle (19...
The success of large pretrained language models (LMs) such as BERT and
R...
In order to simulate human language capacity, natural language processin...
In previous work, artificial agents were shown to achieve almost perfect...
We introduce Multi-SimLex, a large-scale lexical resource and evaluation...
Unsupervised pretraining models have been shown to facilitate a wide ran...
Semantic specialization is the process of fine-tuning pre-trained
distri...
Addressing the cross-lingual variation of grammatical structures and mea...
Distributed representations of sentences have been developed recently to...
Lexical sets contain the words filling the argument positions of a verb ...