Related papers: Multilingual Machine Translation with Hyper-Adapte…
Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a…
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Self-supervised pretrained models are often fine-tuned on parallel data from one or multiple…
Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained language model. Apart from several heuristics, however, there has…
Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…
Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a…
State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing…
The choice of parameter sharing strategy in multilingual machine translation models determines how optimally parameter space is used and hence, directly influences ultimate translation quality. Inspired by linguistic trees that show the…
Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…
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-$k$…
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…
Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific…
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…
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-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…
Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters have not been sufficiently analyzed to understand if PEFT…
Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair seen at training time. However, when a MNMT model is used to translate under domain shift or to…
We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models. By integrating 10 diverse adapter methods into a unified interface, Adapters offers ease of use and…
Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…