Related papers: Field Extraction from Forms with Unlabeled Data

We consider the novel problem of unsupervised domain adaptation of source models, without access to the source data for semantic segmentation. Unsupervised domain adaptation aims to adapt a model learned on the labeled source data, to a new…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…

We propose a novel training scheme using self-label correction and data augmentation methods designed to deal with noisy labels and improve real-world accuracy on a polyphonic audio content detection task. The augmentation method reduces…

In this paper, we propose a novel formula-driven supervised learning (FDSL) framework for pre-training an environmental sound analysis model by leveraging acoustic signals parametrically synthesized through formula-driven methods.…

Motivated by the scarcity of proper labels in an astrophysical application, we have developed a novel technique, called Selfish Evolution, which allows for the detection and correction of corrupted labels in a weakly supervised fashion.…

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to…

Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues,…

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for…

Deploying deep visual models can lead to performance drops due to the discrepancies between source and target distributions. Several approaches leverage labeled source data to estimate target domain accuracy, but accessing labeled source…

Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…

User interaction with voice-powered agents generates large amounts of unlabeled utterances. In this paper, we explore techniques to efficiently transfer the knowledge from these unlabeled utterances to improve model performance on Spoken…

In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions. This work focuses on a challenging case of OOD detection, where no labels for in-domain…

This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…

Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples. The manual labeling…

The challenge of labeling large example datasets for computer vision continues to limit the availability and scope of image repositories. This research provides a new method for automated data collection, curation, labeling, and iterative…

We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another. This is achieved by using unlabeled tokens…

Relation extraction is an important task in structuring content of text data, and becomes especially challenging when learning with weak supervision---where only a limited number of labeled sentences are given and a large number of…

In this paper, we propose a multi-label classification framework to detect multiple speaking styles in a speech sample. Unlike previous studies that have primarily focused on identifying a single target style, our framework effectively…

In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into…