Related papers: Code-switched inspired losses for generic spoken d…

Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate…

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…

Cross-lingual transfer in natural language processing (NLP) models enhances multilingual performance by leveraging shared linguistic knowledge. However, traditional methods that process all data simultaneously often fail to mimic real-world…

Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing significant challenges due to the complexity of semantic modeling and the scarcity of CS…

Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Python, with weaker performance in languages like Rust and OCaml. Since real-world systems…

Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given…

The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in…

Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all…

Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by…

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…

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Multilingual pre-trained models have demonstrated their effectiveness in many multilingual NLP tasks and enabled zero-shot or few-shot transfer from high-resource languages to low resource ones. However, due to significant typological…

We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation. As automatic speech recognition (ASR) systems are being…

Multilingual pre-trained models are known to suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages. We address this issue by introducing language-specific modules, which allows…

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…

This paper aims for a potential architectural improvement for multilingual learning and asks: Can different tasks from different languages be modeled in a monolithic framework, i.e. without any task/language-specific module? The benefit of…

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…

Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively…

Pretrained language models (PLMs) display impressive performances and have captured the attention of the NLP community. Establishing best practices in pretraining has, therefore, become a major focus of NLP research, especially since…

The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to…