Related papers: Bilingual alignment transfers to multilingual alig…

Word embeddings, which represent a word as a point in a vector space, have become ubiquitous to several NLP tasks. A recent line of work uses bilingual (two languages) corpora to learn a different vector for each sense of a word, by…

Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to more languages. In this paper, we introduce MuSR: a…

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…

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.…

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and…

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…

Unsupervised cross-lingual embeddings mapping has provided a unique tool for completely unsupervised translation even for languages with different scripts. In this work we use this method for the task of unsupervised cross-lingual matching…

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their…

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that…

In this paper we propose a model to learn multimodal multilingual representations for matching images and sentences in different languages, with the aim of advancing multilingual versions of image search and image understanding. Our model…

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In…

Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised…

Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that…

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…

Shared multilingual representations are essential for cross-lingual tasks and knowledge transfer across languages. This study looks at the impact of parallel data, i.e. translated sentences, in pretraining as a signal to trigger…

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…

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original…

Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen…