Related papers: How Far Can 100 Samples Go? Unlocking Overall Zero…
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can further…
We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting. While previous work suggests such a relation, it tends to focus on…
Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number…
We investigate whether off-the-shelf deep bidirectional sentence representations trained on a massively multilingual corpus (multilingual BERT) enable the development of an unsupervised universal dependency parser. This approach only…
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…
This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised…
Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based…
We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…
In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. We assume a strict setting with no access to…
In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue…
Prior research diverges on language diversity in LLM fine-tuning: Some studies report benefits while others find no advantages. Through controlled fine-tuning experiments across 132 translation directions, we systematically resolve these…
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training…
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems available to more users is the lack of training data for all but…
Historical text normalization often relies on small training datasets. Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study…
The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages. Despite impressive empirical results and an…
Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via…
Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach…