Paper introduces score embedding for Twitter sentiment analysis of health care issues.
problem Analyzing public opinion on health care plans using social media.
method Score embedding, a neural network model for word representations.
result Score embedding effectively captures sentiment and outperforms existing methods.
New measure helps identify better word embedding compression methods.
problem Challenges in evaluating compressed word embeddings for downstream tasks.
method Proposed eigenspace overlap score and developed generalization bounds.
result Eigenspace overlap score correlates with better downstream performance.
The paper examines the consistency of item embeddings in recommendation systems.
problem The relevance of averaging item embeddings for user or concept representation.
method Proposes an expected precision score to measure consistency and analyzes it theoretically and empirically.
result Real-world averages are less consistent for recommendation compared to theoretical assumptions.
The paper introduces a method for detecting principal communities and embedding vertices.
problem Detecting and embedding vertices in graphs with community structure.
method Principal graph encoder embedding method that detects principal communities and produces vertex embeddings.
result The method successfully detects principal communities and produces accurate vertex embeddings.
T-PSDA improves speaker recognition accuracy on toroidal submanifolds.
problem Improving speaker recognition accuracy on hypersphere embeddings.
method Extends PSDA to model within and between-speaker variabilities in toroidal submanifolds of the hypersphere.
result T-PSDA achieves accuracy on par with cosine scoring on VoxCeleb and large accuracy gains on NIST SRE'21.
Embedding-based methods for knowledge base completion (KBC) learn representations of entities and relations in a vector space, along with the scoring function to estimate the likelihood of relations between entities. The learnable class of scoring functions is designed to be expressive enough to cover a variety of real…
A new activation function improves credit scoring accuracy for imbalanced datasets.
problem Imbalanced datasets in credit scoring lead to underestimation of misclassification costs.
method Introduces ASIG, an asymmetric adjusted Sigmoid function.
result ASIG-embedded classifier outperforms traditional classifiers across various imbalance ratios.
Link prediction is a popular research topic in network analysis. In the last few years, new techniques based on graph embedding have emerged as a powerful alternative to heuristics. In this article, we study the problem of systematic biases in the prediction, and show that some methods based on graph embedding offer le…
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add introspection and error detection capabilities to neural network classifiers. Fir…
A new stable similarity measure for time series using persistent homology.
problem Constructing a robust measure of time series similarity.
method Persistent homology for stability, bi-conditional periodicity score for similarity.
result Stability of the bi-conditional periodicity score under perturbations and dimension reduction.
New document embedding method finds more relevant tech docs.
problem Computing document similarities for technical content.
method Hybrid approach using graph techniques to extract keyphrases and score sentences.
result Proposed methods outperform baselines up to 27% in NDCG.
We propose β-graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment β-score reduces the influence of contamination and robustly measures the difference between the underlying correct expected weights of links and the specified generative m…
We provide a fast L2-embedding for arbitrary accuracy with applications to regression and L1 tasks.
problem Efficiently embedding high-dimensional data while maintaining accuracy.
method Oblivious L2-embedding with dimension independent of accuracy.
result Achieves arbitrary accuracy with constant embedding dimension.
A new method for speaker recognition on hyperspheres improves on PLDA's limitations.
problem Improving speaker recognition on hyperspheres with PLDA's limitations.
method Probabilistic Spherical Discriminant Analysis (PSDA) using Von Mises-Fisher distributions.
result PSDA scores are closed-form and can handle various trials, improving over PLDA.
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
Topological anomaly scores predict return curves in S&P 500 stocks
problem Detecting anomalies in financial time series
method BallMapper, decoder-conditional VAE, Function-on-Function regression
result Anomaly history carries predictive content for return curves
Classifies intrinsically linked tournaments by their score sequences.
problem Classifying intrinsically linked tournaments using their score sequences.
method Examining the score sequences of tournaments and identifying linkless sequences.
result The vast majority of score sequences for 8-vertex tournaments are linkless.
CAEL-MIPS learns embeddings to improve MIPS for better OPE in contextual bandits.
problem High variance in IPS weighting for OPE in large action spaces.
method Context-Action Embedding Learning (CAEL) for MIPS to minimize MSE.
result CAEL-MIPS outperforms baselines in MSE for OPE in contextual bandits.
We study strictly proper scoring rules in the Reproducing Kernel Hilbert Space. We propose a general Kernel Scoring rule and associated Kernel Divergence. We consider conditions under which the Kernel Score is strictly proper. We then demonstrate that the Kernel Score includes the Maximum Mean Discrepancy as a special …
Embeddings in machine learning are low-dimensional representations of complex input patterns, with the property that simple geometric operations like Euclidean distances and dot products can be used for classification and comparison tasks. The proposed meta-embeddings are special embeddings that live in more general in…
INK scores improve OOD detection for classifiers.
problem Detecting out-of-distribution inputs for classification models.
method INK scores operate on constrained latent embeddings modeled as a mixture of hyperspherical embeddings, optimizing in modern neural networks.
result INK establishes a new state-of-the-art in OOD detection.
Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we ex…
LOCA learns standardized data coordinates from measurements.
problem Learning invariant data coordinates from non-linearly deformed manifolds.
method LOCA, a LOcal Conformal Autoencoder, learns an isometric embedding.
result LOCA preserves geometric information while learning invariant coordinates.
The reliable measurement of confidence in classifiers' predictions is very important for many applications and is, therefore, an important part of classifier design. Yet, although deep learning has received tremendous attention in recent years, not much progress has been made in quantifying the prediction confidence of…
Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.
problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
EPP scores interpret model performance better than traditional metrics.
problem Lack of interpretable and stable performance metrics for model selection and hyperparameter tuning.
method Introducing EPP (interpretable predictive power) rating system.
result EPP scores provide probabilistic interpretations of model performance differences.
Probabilistic embeddings improve speaker diarization accuracy.
problem Improving speaker diarization accuracy using embeddings.
method Extracting x-vectors and precision matrices from speech segments, interfacing with PLDA model, applying agglomerative clustering, joint training of PLDA and extractor.
result Joint training of PLDA and probabilistic x-vector extractor yields accuracy gains.
Proposes AML loss function for TransE to improve link prediction in knowledge graphs.
problem Low performance of TransE due to insufficient scores of positive triples.
method Introduces Adaptive Margin Loss (AML) to automatically adjust margin during training.
result AML improves TransE's performance on link prediction tasks in knowledge graphs.
FAMDAD detects anomalies in mixed data using kurtosis-weighted Factor Analysis.
problem Detecting anomalies in high-dimensional mixed data.
method kurtosis-weighted Factor Analysis of Mixed Data (FAMDAD).
result Anomalies are highly separable in the first and last few dimensions of the FAMDAD embedding.
ECS evaluates synthetic CXR images' distributional fidelity.
problem Evaluating synthetic CXR images' distributional fidelity under privacy constraints.
method Characteristic function transforms of feature embeddings.
result ECS uncovers clinically relevant distributional discrepancies.
A new score measures data reliability without ground truth.
problem Assessing reliability of datasets without access to ground truth.
method Define ground-truth-based orderings and propose Gram determinant score.
result Gram determinant score effectively captures data quality across diverse observation processes.
AVH scores measure sample hardness, improving model calibration.
problem CNNs' poor calibration and overconfidence issues.
method AVH score based on normalized angular distance between feature embeddings and target classifiers.
result AVH scores correlate with human visual hardness and improve model calibration.
Paper classifies Brazilian music genres using song lyrics with BLSTM network.
problem Classifying Brazilian music genres from lyrics.
method Used BLSTM network combined with SVM, Random Forest, and word embeddings.
result BLSTM outperforms other models with an F1-score of 0.48.
Regularization improves spectral embedding by focusing on the largest blocks.
problem Improving the quality of spectral embedding for graph data.
method Explained the impact of complete graph regularization on spectral embedding of a block model.
result Regularization forces spectral embedding to focus on the largest blocks, making it less sensitive to noise or outliers.
DKULENOVO team improves speech diarization by 27.5% and 31.7% in DIHARD II.
problem Challenges in speech diarization, especially in distinguishing overlapping speakers.
method Used a combination of VAD, speaker embedding extraction, similarity scoring, clustering, and resegmentation techniques.
result Achieved 18.84% DER in Track1 and 27.90% DER in Track2, reducing baseline DERs by 27.5% and 31.7% respectively.
The paper introduces multicalibration to improve confidence scores in LLMs.
problem Improving the reliability and interpretability of confidence scores for LLMs.
method Forming groupings of prompt/completion pairs correlated with correctness, using clustering and self-annotation. Developing multicalibration algorithms to reduce overfitting.
result Our techniques yield confidence scores that significantly improve calibration and accuracy compared to existing methods.
Extends importance sampling to nonlinear models using adjoint operators.
problem Lack of tools for identifying important data points in nonlinear models.
method Introduces adjoint operator for nonlinear maps, generalizes norm and leverage scores.
result Generalized scores provide approximation guarantees for nonlinear mappings.
BSAC improves credit scoring models by leveraging autoencoders and addressing imbalanced datasets.
problem Imbalanced and heterogeneous credit scoring datasets.
method Bagging Supervised Autoencoder Classifier (BSAC) that uses autoencoders and undersampling.
result BSAC improves classification of loan applicants, demonstrating robustness and effectiveness.
DSE learns sentence embeddings from cross-attention models to speed up sentence-pair similarity computation.
problem Computing sentence-pair similarity is computationally expensive when candidate sentences are large.
method Distilled Sentence Embedding (DSE) based on knowledge distillation from cross-attentive models.
result DSE significantly outperforms ELMO variants and other sentence embedding methods, accelerating computation by several orders of magnitude.
A novel outlier score detects new road infrastructure images.
problem Detecting newly observed road infrastructure images.
method Entropy-based outlier score using directed nearest neighbor graphs.
result High potential of the proposed technique in identifying outliers.
Automates detecting problem statements in peer assessments.
problem Identifying problem statements in peer assessment reviews.
method Used machine learning models including neural networks and traditional classifiers.
result Hierarchical Attention Network classifier achieved 93.1% accuracy.
Quizlet is the most popular online learning tool in the United States, and is used by over 2/3 of high school students, and 1/2 of college students. With more than 95% of Quizlet users reporting improved grades as a result, the platform has become the de-facto tool used in millions of classrooms. In this paper, we expl…
In this paper we present a unified framework for modeling multi-relational representations, scoring, and learning, and conduct an empirical study of several recent multi-relational embedding models under the framework. We investigate the different choices of relation operators based on linear and bilinear transformatio…
We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores. For this purpose, we study different models of hyperbolic space and find that learning embeddings in the Lorentz model is substantially more efficient than in the Poincaré-ball model. We show that the prop…
Paper debiases multiple word embedding biases simultaneously.
problem Reduction of multiple biases in word embeddings.
method Joint multiclass debiasing approach using Word Embeddings Association Test (WEAT).
result Demonstrates reduction or complete elimination of bias in word embeddings.
LITE models improve query-document relevance with learnable late interactions.
problem Improving query-document relevance with lower latency and storage.
method Proposes learnable late-interaction models (LITE) that use factorized query and document embeddings followed by a learnable scorer.
result Empirically, LITE outperforms previous late-interaction models in re-ranking tasks.
Paper proposes a deep learning method to measure domain similarity in Persian texts.
problem Measuring the similarity between different domains of Persian text descriptions.
method Built a dataset of paired texts, used word embeddings and deep neural networks to score similarity, trained on GPU.
result Best model achieved an F1 score of 0.9865.