Related papers: Unsupervised Online Multitask Learning of Behavior…

In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…

Identifying argument components from unstructured texts and predicting the relationships expressed among them are two primary steps of argument mining. The intrinsic complexity of these tasks demands powerful learning models. While…

This paper studies the fast adaptive beamforming for the multiuser multiple-input single-output downlink. Existing deep learning-based approaches assume that training and testing channels follow the same distribution which causes task…

Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…

Large language models (LLMs) have seen increasing popularity in enterprise applications where AI agents and humans engage in objective-driven interactions. However, these systems are difficult to evaluate: data may be complex and unlabeled;…

Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models. Existing methods…

We study methods for learning sentence embeddings with syntactic structure. We focus on methods of learning syntactic sentence-embeddings by using a multilingual parallel-corpus augmented by Universal Parts-of-Speech tags. We evaluate the…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

In this paper, we propose a variational approach to unsupervised sentiment analysis. Instead of using ground truth provided by domain experts, we use target-opinion word pairs as a supervision signal. For example, in a document snippet "the…

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a…

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…

Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic…

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement…

A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…

Question answering has seen significant advances in recent times, especially with the introduction of increasingly bigger transformer-based models pre-trained on massive amounts of data. While achieving impressive results on many…

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion recognition and sentiment analysis, BERT may not lead to…