Related papers: Beyond Bilingual Transfer: Multilingual Code-Switc…
Euphemisms are culturally variable and often ambiguous, posing challenges for language models, especially in low-resource settings. This paper investigates how cross-lingual transfer via sequential fine-tuning affects euphemism detection…
Instruction tuning (IT) is widely used to teach pretrained large language models (LLMs) to follow arbitrary instructions, but is under-studied in multilingual settings. In this work, we conduct a systematic study of zero-shot cross-lingual…
In cross-lingual speech synthesis, the speech in various languages can be synthesized for a monoglot speaker. Normally, only the data of monoglot speakers are available for model training, thus the speaker similarity is relatively low…
Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking…
Multilinguality is a core capability for modern foundation models, yet training high-quality multilingual models remains challenging due to uneven data availability across languages. A further challenge is the performance interference that…
Pixel language models operate directly on images of rendered text, eliminating the need for a fixed vocabulary. While these models have demonstrated strong capabilities for downstream cross-lingual transfer, multilingual pretraining remains…
We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained…
Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end-to-end simultaneous speech translation in a one-to-many…
Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…
Universal cross-lingual sentence embeddings map semantically similar cross-lingual sentences into a shared embedding space. Aligning cross-lingual sentence embeddings usually requires supervised cross-lingual parallel sentences. In this…
Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…
Low-resource languages, by its very definition, tend to be under represented in the pre-training corpora of Large Language Models. In this work, we investigate three low-resource cross-lingual approaches that enable an LLM adapt to tasks in…
Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the…
Why do bilingual speakers code-switch (mix their two languages)? Among the several theories that attempt to explain this natural and ubiquitous phenomenon, the Triggering Hypothesis relates code-switching to the presence of lexical…
Multilingualism refers to the high degree of proficiency in two or more languages in the written and oral communication modes. It often results in language mixing, a.k.a. code-mixing, when a multilingual speaker switches between multiple…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…
Code-switching (CS) is a common linguistic phenomenon exhibited by multilingual individuals, where they tend to alternate between languages within one single conversation. CS is a complex phenomenon that not only encompasses linguistic…
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…
High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still underperform for non-English languages, likely due to a gap in…
Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data. In this paper, we aim to compare the effects of both for the task of sentiment analysis. We work with two…