Related papers: UDapter: Language Adaptation for Truly Universal D…

Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show promise for, e.g., improving low-resource machine translation…

In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss, that can adapt to the…

Neural speech synthesis, or text-to-speech (TTS), aims to transform a signal from the text domain to the speech domain. While developing TTS architectures that train and test on the same set of speakers has seen significant improvements,…

Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input, which poses challenges in terms of balancing quality and latency of the translation. The wait-$k$…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for…

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how…

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommendation performance in…

While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting.…

Previous work on Universal Transformers (UTs) has demonstrated the importance of parameter sharing across layers. By allowing recurrence in depth, UTs have advantages over standard Transformers in learning compositional generalizations, but…

We demonstrate that a dependency parser can be built using a credit assignment compiler which removes the burden of worrying about low-level machine learning details from the parser implementation. The result is a simple parser which…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

Exemplar-based image editing applies a transformation defined by a source-target image pair to a new query image. Existing methods rely on a pair-of-pairs supervision paradigm, requiring two image pairs sharing the same edit semantics to…

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem in data integration…

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…