Study shows noisy historical data can still predict future text classification well.
problem Challenges in text classification with noisy, historical data.
method Examined how performance metrics on noisy data reflect future model performance.
result Noisy training data can be used to build effective prediction models for cleaner inputs.
Pangloss improves entity linking in noisy text environments.
problem Entity linking in non-grammatical, loosely-structured text.
method Combines probabilistic key phrase identification and semantic similarity engine.
result Better than state-of-the-art results (>5% in F1).
ECN framework improves training on noisy structured labels.
problem Structured errors in fine-grained annotations lead to biased models.
method Error-Correcting Networks (ECN) framework.
result ECN improves fine-grained annotation prediction.
FUNSD dataset tackles noisy scanned forms, offering comprehensive annotations.
problem Extracting and structuring textual content from noisy scanned documents.
method Comprehensive dataset with real, fully annotated forms, including text detection, OCR, layout analysis, and entity linking.
result First publicly available dataset for form understanding, addressing challenges in noisy scanned documents.
A novel method extracts topological features from word embeddings for text classification.
problem High dimensional and noisy text representations in natural language processing.
method Persistent homology for topological data analysis on word embeddings.
result Topological features outperform conventional text mining features on long textual documents.
New metric compares noisy neural trajectories using optimal transport.
problem Existing metrics fail to capture differences in noisy, dynamic neural responses.
method Proposed an optimal transport distance metric for Gaussian processes.
result Metric effectively compares neural dynamics in different systems.
Compressed LLM embeddings improve noisy regression tasks without overfitting.
problem Noisy regression tasks with high signal-to-noise ratios.
method Comparison of embedding compression techniques using autoencoder hidden representations.
result Compression improves performance on noisy tasks like financial return prediction.
Framework tackles class imbalance and noisy labels in active learning.
problem Class imbalance and noisy labels in real-world datasets.
method Uses foundation model priors to select informative samples for active learning.
result Substantial annotation savings (over 50%) with preserved performance and robustness.
Expands weak supervision by allowing partial labels from multiple noisy sources.
problem Creating models without labeled data using heuristic labelers.
method Probabilistic generative model estimating partial label accuracies.
result Improved model accuracy on various tasks (8.6% on text, comparable to zero-shot methods on images).
Improved POS tagging for Twitter data with limited annotations.
problem Low-quality user-generated text for POS tagging.
method Domain adaptation using neural networks with feature embeddings and pre-trained embeddings.
result 90% tagging accuracy on German Tweets.
Enhances GNNs with text features for better fake news detection.
problem Detecting disinformation on social media using GNNs.
method Integrates Transformer-based textual features into GNNs.
result Contextual text representations improve GNN performance by 33.8% in Macro F1.
Paper introduces new indicators for forecasting crude oil prices using short news headlines.
problem Forecasting crude oil prices from short, noisy news headlines using LDA.
method Developed two novel indicators for topic and sentiment from short text data, and applied AdaBoost.RT.
result AdaBoost.RT with the proposed indicators outperforms benchmarks in crude oil forecasting.
Debiasing techniques can worsen gender bias in text classification, but a tweak improves both.
problem Debiasing techniques can inadvertently increase gender bias in text classification.
method Investigated traditional debiasing techniques and found they worsen bias. Suggested a minor adjustment.
result A minor adjustment to debiasing techniques can reduce gender bias while maintaining high classification accuracy.
Self-distillation improves model performance in noisy label settings.
problem Improving model accuracy in supervised learning with noisy labels.
method Analyzes self-distillation in two supervised learning problems with noisy labels, using theoretical and empirical approaches.
result Optimal self-distillation parameter is greater than 1 in high label noise regimes, outperforming traditional methods.
Improved private AdaGrad achieves faster convergence rates for convex functions.
problem Private empirical risk minimization with differential privacy.
method Noisy AdaGrad with knowledge of gradient subspace geometry.
result Faster convergence rates for convex functions, bypassing traditional bounds.
New loss function helps models avoid noisy labels, improving robustness.
problem Designing robust models for datasets with noisy labels.
method Introduced a gambler's loss function that encourages models to abstain from learning noisy data points.
result Training with gambler's loss leads to improved robustness and generalization across various tasks.
SoulMate links short texts through multi-aspect embeddings.
problem Linking authors of noisy, ambiguous short texts.
method Neural network-based temporal-textual framework generating author subgraphs.
result Higher performance in linking short-text authors compared to competitors.
Paper shows pretrained models can categorize Thai social media content effectively.
problem Lack of labeled data for Thai social media content classification.
method Pretrained language models on a large noisy Thai social media corpus, fine-tuned for downstream tasks.
result State-of-the-art results achieved on Thai social text categorization tasks.
Qwen3-8B outperforms classical models in financial text classification.
problem Financial text classification for trading systems and sentiment analysis.
method Noisy Embedding Instruction Finetuning and Rank-stabilized Low-Rank Adaptation.
result Qwen3-8B achieves better classification accuracy and fewer training epochs.
Enhanced regime shifts detection using unstructured text and financial data.
problem Detecting regime shifts in financial markets is challenging due to noisy and multicollinear data.
method Combines LLM reasoning on unstructured text and statistical validation on financial time series.
result Framework achieves F1 score of 0.82, outperforming pure data-driven methods.
Proposes BONMI for integrating noisy matrices from multi-source data.
problem Integrating noisy matrices from multi-source data with block-wise missingness.
method Exploits orthogonal Procrustes problem to align eigenspaces and completes missing blocks.
result Statistical rate for eigenspace of underlying matrix comparable to independently missing assumption.
Paper proposes a new meta-learning approach for correcting noisy labels.
problem Learning with noisy labels in machine learning models.
method Meta-learned instance re-weighting approach extended to label correction problem.
result Proposed MLC (Meta Label Correction) framework achieves large improvements over previous methods.
Model clusters authors and topics in short texts like social media posts.
problem Analysis of short texts is difficult due to brevity and lack of context.
method Expands Latent Dirichlet Allocation to model word dependencies and cluster users.
result Improves topic and user clustering, outperforming traditional methods.
Paper proposes a method to train deep text classification models robust to label noise.
problem Training deep text classification models with noisy labels.
method Introduces a non-linear processing layer (noise model) into CNN architecture, learned jointly with CNN weights.
result The approach enables better sentence representations and robustness to extreme label noise.
LLmFPCA-detect detects anomalies in sparse longitudinal text data using LLMs and mFPCA.
problem Challenges in detecting patterns and anomalies in sparse longitudinal textual data.
method Pairs LLM-based text embeddings with mFPCA to detect clusters and anomalies.
result LLmFPCA-detect outperforms state-of-the-art baselines on Amazon and Wikipedia datasets.
DPNR preserves privacy of text representations using differential privacy.
problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.
An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification based on the SVMs classifier, in text independent mode. This approach combines features based on conven…
Efficiently use expert time in relation extraction by using distant supervision and active learning.
problem Scarcity of labeled data in relation extraction, especially with expert time constraints.
method Use distant supervision to label data and active learning to refine results with expert feedback.
result Improved relation extraction results with active learning from expert feedback.
A two-stage optimization framework reduces label noise in federated learning.
problem Label noise from noisy clients degrades federated learning model performance.
method MaskedOptim framework: detects noisy clients, corrects labels, and aggregates models robustly.
result Our framework improves model robustness and data quality in federated learning.
HRT uses bi-level reinforcement learning to optimize stock selection and execution in multi-asset equity markets.
problem Optimizing automated equity trading decisions under risk, turnover, and transaction costs.
method Hierarchical Reinforced Trader (HRT) framework that separates selection and execution decisions.
result HRT outperforms other methods in learning-based return-risk-cost trade-offs, improving Sharpe ratio and reducing turnover.
Self-training improves neural sequence generation by correcting incorrect predictions.
problem Improving neural sequence generation models using unlabeled data.
method Injecting pseudo-parallel data (model predictions) into the labeled dataset and using dropout as a regularizer.
result Noisy self-training significantly improves performance on machine translation and text summarization benchmarks.
Model learns association between text and speech without paired data.
problem Learning association between text and speech with limited paired data.
method Noisy channel generative model with variational inference and KL encoder loss.
result Tiny paired data (5 minutes) sufficient to learn association.
Local graph clustering improves with noisy labels, enhancing accuracy and performance.
problem Local graph clustering with noisy labels for node information.
method Constructing a weighted graph with noisy labels and using diffusion-based clustering.
result Diffusion in the weighted graph yields more accurate recovery of target clusters.
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora…
Confident learning estimates label quality by identifying and correcting noisy data.
problem Label quality in datasets, especially in noisy environments.
method Combines principles of pruning, probabilistic thresholds, and ranking to estimate noise and uncorrupted labels.
result Generalized CL framework that provably finds label errors and improves model accuracy.
Improved text summarization using neural semantic encoders with hierarchical structure.
problem Capturing long-term dependencies in text summarization.
method Proposed a novel hierarchical Neural Semantic Encoder (NSE) model augmented with lemma and PoS tags.
result Significantly outperformed state-of-the-art models in ROUGE metric.
Improved fine-tuning with regularization and robustness for noisy labels.
problem Fine-tuning pre-trained models on small datasets can lead to overfitting and memorization.
method PAC-Bayes generalization bound analysis, layer-wise regularization, self-label-correction, label-reweighting.
result Improves performance by 1.76% on average for image classification tasks and 0.75% for few-shot classification.
Optimistic Q-learning reduces sample complexity for systems with known dynamics.
problem Sample efficiency in reinforcement learning with partial dynamics knowledge.
method Optimistic Q-learning algorithm for systems with additive disturbance model.
result Achieves i l d e O ( e x t P o l y ( H ) T ) ilde{\mathcal{O}}( ext{Poly}(H)\sqrt{T}) i l d e O ( e x t P o l y ( H ) T ) regret under perfect knowledge of dynamics. This paper establishes conditions for sparse signal recovery with sparse measurements.
problem Recovering the support of a sparse signal using noisy projections with sparse measurement matrices.
method Establishes sufficient conditions for successful sparse recovery using sparse measurement matrices.
result A phase transition threshold for sparse recovery in the sparse setting is discovered, revealing a trade-off between sampling complexity and measurement sparsity.
GCTM integrates GCN into topic models for better topic learning from data streams.
problem Learning hidden topics from short and noisy data streams with concept drift.
method Proposes a graph convolutional topic model (GCTM) that learns from a knowledge graph and old data.
result Significantly better performance in probabilistic predictive measures and topic coherence.
New method reduces memorization in diffusion models without sacrificing image quality.
problem Diffusion models often memorize training data, especially with small datasets.
method Train models using noisy data at large noise scales to reduce memorization.
result Significant reduction in memorization without compromising image quality.
Faster diffusion-based models generate data with fewer steps.
problem Slow and costly diffusion-based generative models.
method Truncate diffusion process to generate data more efficiently.
result Truncated models provide consistent improvements in performance.
New methods for unsupervised learning of word and entity representations.
problem Learning distributed representations of words and entities from text and knowledge bases.
method MVLSA for words and NVSE for entities, both unsupervised learning methods.
result MVLSA and NVSE outperform state-of-the-art models in word and entity representation learning.
New framework combines semi-supervised data programming with subset selection for improved text classification.
problem Sub-optimal performance in data programming with noisy labelling functions.
method Introduces a framework \model for semi-supervised data programming that uses joint models and subset selection.
result Significantly outperforms state-of-the-art on seven datasets.
A bandit algorithm reduces regret in noisy, communication-constrained feedback.
problem Distributed stochastic multi-armed bandit with noisy, communication-constrained feedback.
method Proposes a multi-phase bandit algorithm, UE-UCB++, that matches an information-theoretic lower bound.
result Matches an information-theoretic lower bound of Ω(√(KT/σ²)) on the minimax regret.
BAEN-SVM improves SVM robustness to noisy data.
problem Noise and geometric irrationalities in SVM.
method Bounded asymmetric elastic net loss combined with SVM.
result BAEN-SVM is robust to noise and geometrically well-defined.
A new method for weakly supervised learning that improves model accuracy.
problem Training machine learning models with precise labels is expensive; weak supervision provides a low-cost alternative.
method Data consistent weak supervision algorithm that searches over classifiers to find plausible labelings, considering features of the training data and estimating labels for low/no coverage data.
result Empirically, the method significantly outperforms state-of-the-art weak supervision methods on text and image classification tasks.
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.