This study examines how imbalanced training data affects author name disambiguation.
problem The impact of imbalanced training data on machine learning for author name disambiguation.
method Training three classifiers (Logistic Regression, Naïve Bayes, Random Forest) on multiple labeled datasets with various positive-negative training data ratios.
result Increasing negative training data can improve disambiguation performance but with diminishing returns.
A new method for name disambiguation in academic networks using multi-view attention and recurrent neural networks.
problem Disambiguating authors with the same name in large-scale academic networks.
method Multi-view Attention-based Pairwise Recurrent Neural Network (MA-PairRNN) that divides papers into blocks based on author attributes and merges blocks of the same author.
result MA-PairRNN significantly improves name disambiguation performance on real-world datasets.
This study improves author disambiguation without supervision using feature overlap.
problem Author name homonymy in the Web of Science.
method Probabilistic similarity measure based on feature overlap for agglomerative clustering.
result Our approach outperforms the trivial baseline and is state-of-the-art.
Author name disambiguation in bibliographic databases is the problem of grouping together scientific publications written by the same person, accounting for potential homonyms and/or synonyms. Among solutions to this problem, digital libraries are increasingly offering tools for authors to manually curate their publica…
Paper develops neural network for Mandarin polyphone disambiguation.
problem Homograph problem in Mandarin Chinese text-to-speech.
method Bidirectional RNN for context, prediction network for mapping embeddings to pronunciations.
result Achieves 94.69% accuracy on polyphonic character dataset.
EviTrack improves sequential prediction in delayed disambiguation scenarios.
problem Challenges in sequential prediction with delayed disambiguation where early observations are ambiguous.
method EviTrack operates over latent trajectories, applying evidence- and likelihood-ratio-based selection to delay commitment until supported by data.
result EviTrack outperforms sampling-based baselines in a controlled synthetic benchmark, achieving faster post-disambiguation recovery.
Paper proposes an algorithm to recover full supervision from weakly labeled data.
problem Machine learning requires expensive data annotation, motivating the use of weak supervision.
method The paper introduces a disambiguation principle and an empirical disambiguation algorithm for partial labelling.
result The algorithm achieves exponential convergence rates under learnability assumptions.
Model learns to discover and disambiguate entities and relations in text streams.
problem Learning to follow and resolve mentions in a continuous text stream.
method End-to-end trainable memory network for online, one-shot learning.
result Improves disambiguation and discovery skills with minimal supervision.
A new system learns entity representations to improve local entity disambiguation.
problem Local entity disambiguation in text.
method Entity-ELMo (E-ELMo) approach for contextual entity representation.
result Outperforms state-of-the-art models by 0.5% on AIDA test-b.
Improves medical note processing by training model on related concepts and global context.
problem Scarce and imbalanced labeled training data limits generalizability of automated abbreviation disambiguation models.
method Data augmentation using related medical concepts and global context information within medical notes.
result Model accuracy improved by almost 14% on CASI dataset and 4% on i2b2 dataset.
A coloring scheme improves graph neural networks for node disambiguation.
problem Improving graph neural networks' ability to distinguish identical node attributes.
method Introducing a graph neural network called Colored Local Iterative Procedure (CLIP) that uses colors to disambiguate node attributes.
result CLIP is a universal approximator of continuous functions on graphs with node attributes.
DivDis learns diverse hypotheses from underspecified data to improve robustness.
problem Learning from underspecified datasets leads to multiple equally viable solutions, causing out-of-distribution issues.
method DivDis framework: 1) learns diverse hypotheses using unlabeled test data, 2) selects one hypothesis with minimal additional supervision.
result DivDis finds robust features in image and natural language processing problems.
Framework tracks evolving news stories across multiple sources.
problem Tracking evolving news stories across diverse sources and formats.
method Cross-domain story tracking approach using entity graphs and learning-to-rank.
result Outperforms state-of-the-art methods for real-time story tracking.
New method clusters unknown music artists using audio metrics.
problem Disambiguating large catalogs of unknown artists.
method Metric learning from audio data with negative sampling.
result Our method outperforms a classifier-based approach when audio data is available.
Vector representations of words have heralded a transformational approach to classical problems in NLP; the most popular example is word2vec. However, a single vector does not suffice to model the polysemous nature of many (frequent) words, i.e., words with multiple meanings. In this paper, we propose a three-fold appr…
Sparse-mode DMD disambiguates local and global modes in spatiotemporal data.
problem Disambiguating local and global modes in spatiotemporal data.
method Sparse-mode DMD with sparsity-promoting regularization.
result Explicitly constructs discrete and continuous spectra.
Paper proposes FOFE for efficient WSD.
problem Word sense disambiguation (WSD) problem.
method Fixed-size ordinally forgetting encoding (FOFE) combined with FFNN.
result FOFE-based FFNN achieves comparable performance to state-of-the-art at lower cost.
PML-GAN tackles noisy multi-label annotations using adversarial learning.
problem Learning multi-label models from noisy, overcomplete annotations.
method PML-GAN uses a disambiguation network and a generative adversarial network to map noisy labels to clean labels and data samples.
result PML-GAN achieves state-of-the-art performance on partial multi-label learning datasets.
Efficient autoregressive entity linking with correction for faster, more accurate results.
problem High computational cost and non-parallelizable decoding in autoregressive entity linking.
method Parallelizes autoregressive linking across all mentions, uses a shallow decoder, and adds a discriminative correction term.
result 70 times faster and more accurate than previous methods, outperforming state-of-the-art approaches.
DKPCA improves WSD accuracy with scarce labeled data.
problem Word sense disambiguation in natural language processing.
method DKPCA combines Kernel PCA and Semantic Diffusion Kernel.
result DKPCA outperforms SVM and KPCA on SensEval data.
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).
FONDUE identifies ambiguous nodes in networks for better analysis.
problem Ambiguous nodes in network data.
method Network embedding for node disambiguation.
result FONDUE outperforms existing methods in ambiguous node identification.
Improves biomedical entity linking with latent type modeling.
problem Lack of fine-grained type information for entity disambiguation.
method Jointly models entity disambiguation and latent type learning without direct supervision.
result Significant performance improvements over state-of-the-art techniques.
This article reviews entity resolution methods and their applications.
problem Integrating information from multiple sources to clean and accurately link records.
method Clustering, semi- and fully supervised methods, canonicalization.
result Modern probabilistic record linkage has been foundational.
Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers…
The study quantifies uncertainty to improve model calibration and disambiguate annotator and data bias in emotion recognition.
problem Improving model interpretability and disambiguating bias in complex tasks like emotion recognition.
method Used a modified Monte Carlo dropout approach to quantify epistemic and aleatoric uncertainty.
result Identified a significant correlation between aleatoric uncertainty and human annotator disagreement.
Active inference selects actions to maximize information gain, aiding structure learning.
problem Learning the structure of underlying world models.
method Active inference selects actions based on expected free energy, which includes information gain and value.
result Actions that maximize information gain help disambiguate among alternative models.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
A CNN for lidar data improves understanding of moving vehicles.
problem Disambiguating the motion of vehicles from a single lidar sensor.
method Proposes a CNN architecture trained with pretext tasks including image data.
result CNN outperforms without image data at test time.
We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…
We describe our language-independent unsupervised word sense induction system. This system only uses topic features to cluster different word senses in their global context topic space. Using unlabeled data, this system trains a latent Dirichlet allocation (LDA) topic model then uses it to infer the topics distribution…
In this work we introduce a mixture of GPs to address the data association problem, i.e. to label a group of observations according to the sources that generated them. Unlike several previously proposed GP mixtures, the novel mixture has the distinct characteristic of using no gating function to determine the associati…
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this …
Sparse principal component analysis (SPCA) has emerged as a powerful technique for modern data analysis, providing improved interpretation of low-rank structures by identifying localized spatial structures in the data and disambiguating between distinct time scales. We demonstrate a robust and scalable SPCA algorithm b…
New deep learning method preserves orientation in shape matching.
problem Symmetry issues in shape matching.
method Orientation-aware functional maps using complex functional representations and DiffusionNet.
result Stable correspondence predictions with robust orientation preservation.
This research explores using kernels in the softmax layer for better contextual word classification.
problem Improving contextual word classification accuracy.
method Replacing the inner product in the softmax layer with various kernel functions and comparing their performance.
result Different kernel settings yield varying performance in contextual word classification tasks.
Cryptonite tests NLP models with cryptic crossword clues.
problem Ambiguity in language poses a challenge for NLP models.
method Cryptic crossword dataset based on cryptic clues.
result Fine-tuning T5-Large on Cryptonite achieves only 7.6% accuracy.
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private information from multiple views of the data. In contrast to previous approaches, we i…
We introduce the author-topic model, a generative model for documents that extends Latent Dirichlet Allocation (LDA; Blei, Ng, & Jordan, 2003) to include authorship information. Each author is associated with a multinomial distribution over topics and each topic is associated with a multinomial distribution over words.…
A new graph encoder StarE models hyper-relational KGs, improving link prediction.
problem Link prediction on hyper-relational KGs suffers from flawed benchmarks.
method Message passing based graph encoder StarE.
result StarE outperforms existing approaches in link prediction across multiple benchmarks.
Enhanced word embeddings boost multiclass text classification accuracy.
problem Improving multiclass text classification accuracy using pre-trained embeddings.
method Proposed word-class embeddings (WCEs) to enhance pre-trained word embeddings.
result WCEs significantly improve multiclass text classification accuracy.
Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either simply treating each candidate label equally or iteratively identifying the true…
Splat Regression Models use mixtures of bump functions to approximate complex data.
problem Approximating complex data with high interpretability and accuracy.
method Model outputs are mixtures of heterogeneous and anisotropic bump functions (splats) weighted by output vectors. Fitting splat models reduces to optimization over mixing measures using Wasserstein-Fisher-Rao gradient flows.
result Unified theoretical framework for Gaussian Splatting and flexible approach for diverse problems.
Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adver…
Machine learning has become pervasive in multiple domains, impacting a wide variety of applications, such as knowledge discovery and data mining, natural language processing, information retrieval, computer vision, social and health informatics, ubiquitous computing, etc. Two essential problems of machine learning are …
Extracts roles of authors from biomedical papers.
problem Lack of machine-readable author roles in biomedical papers.
method Statistical analysis of roles, Open Information Extraction, Naïve Bayes approach.
result Extracts roles with precision of 0.68, recall of 0.48, and F1 of 0.57.
AttViz offers online visualizations of neural language model attention mechanisms.
problem Limited interpretability of neural language models.
method Online toolkit for exploring self-attention mechanisms.
result Visualizations help understand model decision-making.