相关论文: Active Learning for Multilingual Fingerspelling Co…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Pretrained multilingual models enable zero-shot learning even for unseen languages, and that performance can be further improved via adaptation prior to finetuning. However, it is unclear how the number of pretraining languages influences a…

Spoken dialog systems need to be able to handle both multiple languages and multilinguality inside a conversation (\textit{e.g} in case of code-switching). In this work, we introduce new pretraining losses tailored to learn multilingual…

Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and…

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have…

Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method…

Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize this bias and investigate the situations in which it can be…

Communicative efficiency is a key topic in linguistics and cognitive psychology, with many studies demonstrating how the pressure to communicate with minimal effort guides the form of natural language. However, this phenomenon is rarely…

Structured prediction is ubiquitous in applications of machine learning such as knowledge extraction and natural language processing. Structure often can be formulated in terms of logical constraints. We consider the question of how to…

Active learning is a setting in which a student queries a teacher, through membership and equivalence queries, in order to learn a language. Performance on these algorithms is often measured in the number of queries required to learn a…

Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the reasons behind this phenomenon, focusing on the pre-training…

The success of multilingual pre-trained models is underpinned by their ability to learn representations shared by multiple languages even in absence of any explicit supervision. However, it remains unclear how these models learn to…

There have been recent advances in computer-based recognition of isolated, citation-form signs from video. There are many challenges for such a task, not least the naturally occurring inter- and intra- signer synchronic variation in sign…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Many state-of-the-art delineation methods rely on supervised machine learning algorithms. As a result, they require manually annotated training data, which is tedious to obtain. Furthermore, even minor classification errors may…

A persistent challenge in sign language video processing, including the task of sign to written language translation, is how we learn representations of sign language in an effective and efficient way that preserves the important attributes…

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL…

Large pretrained language models have been performing increasingly well in a variety of downstream tasks via prompting. However, it remains unclear from where the model learns the task-specific knowledge, especially in a zero-shot setup. In…

Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised…

Recent advances in deep learning have resulted in great successes in various applications. Although semi-supervised or unsupervised learning methods have been widely investigated, the performance of deep neural networks highly depends on…