Related papers: Adapting Language Models via Token Translation
Sparse auto-encoders (SAEs) have become a prevalent tool for interpreting language models' inner workings. However, it is unknown how tightly SAE features correspond to computationally important directions in the model. This work…
Text simplification (TS) can be viewed as monolingual translation task, translating between text variations within a single language. Recent neural TS models draw on insights from neural machine translation to learn lexical simplification…
Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade systems, which are often composed of recognition, translation…
Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…
Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…
Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in…
Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…
Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks. However, they have recently been shown to suffer limitation in compositional generalization, failing to effectively learn the…
In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture…
Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…
Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may…
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and generation tasks. In this paper, we investigate prompt tuning for semantic parsing -- the task of…
Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens…
Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…
Large-scale transformer models have emerged as a powerful tool for semantic communication systems, enabling edge devices to extract rich representations for robust inference across noisy wireless channels. However, their substantial…
Speech-to-Speech Translation (S2ST) models transform speech from one language to another target language with the same linguistic information. S2ST is important for bridging the communication gap among communities and has diverse…
State-of-the-art language models are autoregressive and operate on subword units known as tokens. Specifically, one must encode the conditioning string into a list of tokens before passing to the language models for next-token prediction.…
Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…
Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…
Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…