arXiv research

Study explores how to explain deep neural networks using interactive naming.

The paper proposes incentivizing human annotators with 'golden questions' to improve data quality.

A new method uses triplet embeddings to improve human annotation for hidden constructs.

Framework uses human annotations to make models robust to spurious correlations.

Paper proposes an alternative to anchor points for learning with noisy labels.

CPATTA uses conformal prediction for efficient test-time adaptation.

SPIN converts weak LLMs to strong ones using self-play.

Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.

Standard myopic active learning assumes that human annotations are always obtainable whenever new samples are selected. This, however, is unrealistic in many real-world applications where human experts are not readily available at all times. In this paper, we consider the single shot setting: all the required samples s…

New method pools labels from similar data items to improve learning from small samples.

XRM discovers environments without human annotations for OOD methods.

Survey on AL strategies for cost-effective annotation in classification.

Graph neural network predicts optimal coarse-grained mapping operators.

Study real-world noisy labels from human annotations for better understanding.

Bayesian algorithms improve crowdsourcing with label and instance constraints.

Hybrid approach combines user feedback and machine learning for predicting user satisfaction.

Evaluates change point detection algorithms on real-world data.

Paper proposes an efficient method for bounding box annotation in object detection.

This paper surveys scalable automated alignment methods for LLMs.

Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturally…

Model accurately gates ocean microbes from high-frequency flow cytometry data.

A new deep learning framework selects representative samples for unsupervised learning.

IAL uses interactive learning to improve model performance with minimal human feedback.

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the impo…

Analysis of flow cytometry data is an essential tool for clinical diagnosis of hematological and immunological conditions. Current clinical workflows rely on a manual process called gating to classify cells into their canonical types. This dependence on human annotation limits the rate, reproducibility, and complexity …

Extraction of missing attribute values is to find values describing an attribute of interest from a free text input. Most past related work on extraction of missing attribute values work with a closed world assumption with the possible set of values known beforehand, or use dictionaries of values and hand-crafted featu…

Curriculum learning strategies improve GAN training speed and quality.

Music FaderNets learns high-level musical qualities from low-level attributes.

Paper connects Plackett-Luce and Cox models for preference estimation.

Improved crypto market forecasting using historical price reactions to tweets.

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot l…

New method removes MRI banding without post-processing.

Sensor data has been playing an important role in machine learning tasks, complementary to the human-annotated data that is usually rather costly. However, due to systematic or accidental mis-operations, sensor data comes very often with a variety of missing values, resulting in considerable difficulties in the follow-…

Syntactic constituency parsing is a fundamental problem in natural language processing and has been the subject of intensive research and engineering for decades. As a result, the most accurate parsers are domain specific, complex, and inefficient. In this paper we show that the domain agnostic attention-enhanced seque…

Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper,…

Experiment tested active learning for Thai text segmentation.

Paper uses AC-GAN to generate high-quality relational sentences for relation extraction.

Study evaluates gender bias in relation extraction systems.

Improved accuracy in a commercial assistant by smartly selecting new training data.

When using active learning, smaller batch sizes are typically more efficient from a learning efficiency perspective. However, in practice due to speed and human annotator considerations, the use of larger batch sizes is necessary. While past work has shown that larger batch sizes decrease learning efficiency from a lea…

In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels. In this problem, the data consist of a set of input time series, and supervision is provided by a sequence of noisy time stamps corresponding to the occurrence of positive class e…

This work analyzes two methods for combining multiple binary labels in bipartite ranking.

Novel active learning framework using sparse approximation for efficient model training.

Similarity between objects is multi-faceted and it can be easier for human annotators to measure it when the focus is on a specific aspect. We consider the problem of mapping objects into view-specific embeddings where the distance between them is consistent with the similarity comparisons of the form "from the t-th vi…

Paper uses knowledge bases to discover new relations from text.

System identifies related passages for easier text comprehension.

k-Rater reliability corrects under-reporting of aggregated data reliability.

Convex clustering can only learn convex clusters, with significant gaps between clusters.