Related papers: Generating and Exploiting Large-scale Pseudo Train…
We report on novel investigations into training models that make sentences concise. We define the task and show that it is different from related tasks such as summarization and simplification. For evaluation, we release two test sets,…
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the…
Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…
Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world…
Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…
Recently developed deep neural networks achieved state-of-the-art results in the subject of 6D object pose estimation for robot manipulation. However, those supervised deep learning methods require expensive annotated training data. Current…
Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tasks like mathematical reasoning. However, developing PRMs is…
Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the ground truth availability is limited with real-world noisy…
Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling. There are two common strategies to manage the impact of such noise.…
Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…
In the short text, the extremely short length, feature sparsity, and high ambiguity pose huge challenges to classification tasks. Recently, as an effective method for tuning Pre-trained Language Models for specific downstream tasks,…
Recently self-supervised learning has been proposed in the field of human activity recognition as a solution to the labelled data availability problem. The idea being that by using pretext tasks such as reconstruction or contrastive…
We study the problem of few-shot learning-based denoising where the training set contains just a handful of clean and noisy samples. A solution to mitigate the small training set issue is to pre-train a denoising model with small training…
Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…
The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks human to annotate data that it perceived as…
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…
In pro-drop language like Arabic, Chinese, Italian, Japanese, Spanish, and many others, unrealized (null) arguments in certain syntactic positions can refer to a previously introduced entity, and are thus called anaphoric zero pronouns. The…
Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…
Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that…