Related papers: Adapting Language Models via Token Translation
Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to…
Multilingual pretrained models are effective for machine translation and cross-lingual processing because they contain multiple languages in one model. However, they are pretrained after their tokenizers are fixed; therefore it is difficult…
Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…
Applying the Transformer architecture on the character level usually requires very deep architectures that are difficult and slow to train. These problems can be partially overcome by incorporating a segmentation into tokens in the model.…
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead. While existing model compression methods strive to reduce the number of model parameters while…
While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…
Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…
It has been known that direct speech-to-speech translation (S2ST) models usually suffer from the data scarcity issue because of the limited existing parallel materials for both source and target speech. Therefore to train a direct S2ST…
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with minimal or no reduction…
Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized on general-purpose corpora. These tokenizers' fixed vocabularies often fail to…
One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…
Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…
We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…
Large language models pretrained on general-domain corpora often exhibit tokenization inefficiencies when applied to specialized domains. Although continual pretraining for domain adaptation partially alleviate performance degradation, it…
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our…
Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularly, auto-regressive language models generate texts token by…
The choice of tokenizer can profoundly impact language model performance, yet accessible and reliable evaluations of tokenizer quality remain an open challenge. Inspired by scaling consistency, we show that smaller models can accurately…