Related papers: Enhancing Cross-lingual Transfer via Phonemic Tran…
The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource…
Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for…
Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital divide by incorporating…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task. Utilizing…
Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…
Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…
Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text…
Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…
This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pairs of sign videos, gloss annotations and texts, which are…
We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new…
Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units, widening access to Natural Language Processing (NLP) technologies for languages with limited written resources. However, progress…
One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data collection for machine learning models for this task is…
Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to…
Automatic evaluation metrics are essential for building multilingual translation systems. The common practice of evaluating these systems is averaging metric scores across languages, yet this is suspicious since metrics may suffer from…
Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining corpora or access to typologically similar languages. In…
Cross-lingual pre-training has achieved great successes using monolingual and bilingual plain text corpora. However, most pre-trained models neglect multilingual knowledge, which is language agnostic but comprises abundant cross-lingual…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…
Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory…
Large-scale cross-lingual language models (LM), such as mBERT, Unicoder and XLM, have achieved great success in cross-lingual representation learning. However, when applied to zero-shot cross-lingual transfer tasks, most existing methods…