Related papers: Zero-Shot Tokenizer Transfer
Large language models (LLMs) have exerted a considerable impact on diverse language-related tasks in recent years. Their demonstrated state-of-the-art performance is achieved through methodologies such as zero-shot or few-shot prompting.…
Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens.\footnote{In this paper words and subwords are referred to as \textit{tokens}…
Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these…
Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…
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…
Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages that were not included in the fine-tuning process. While…
Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…
Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate responses to specific queries. This deficiency can be traced…
Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the…
Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…
Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…
Understanding representation transfer in multilingual neural machine translation (MNMT) can reveal the reason for the zero-shot translation deficiency. In this work, we systematically analyze the representational issue of MNMT models. We…
Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…
Today's large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than…
Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they have difficulty with zero-shot translation: translating…
The rapid advancement in large foundation models is propelling the paradigm shifts across various industries. One significant change is that agents, instead of traditional machines or humans, will be the primary participants in the future…
Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dialogue corpora and…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\textit{Franken-Adapter}$, a modular…
Zero-shot cross-lingual transfer by fine-tuning multilingual pretrained models shows promise for low-resource languages, but often suffers from misalignment of internal representations between languages. We hypothesize that even when the…