FLDCRF improves sequence labeling performance with latent dynamics interactions.
problem Sequence labeling with improved performance and latent dynamics interactions.
method Factored Latent-Dynamic Conditional Random Fields (FLDCRF) with multiple latent dynamics interactions.
result FLDCRF outperforms state-of-the-art models across multiple datasets.
Several machine learning problems arising in natural language processing can be modeled as a sequence labeling problem. We provide Gaussian process models based on pseudo-likelihood approximation to perform sequence labeling. Gaussian processes (GPs) provide a Bayesian approach to learning in a kernel based framework. …
NCRF transducers improve sequence labeling across tasks.
problem Sequence labeling with non-linear node potentials.
method Two RNNs: one for features and one for long-range label dependencies.
result Consistent improvements over linear-chain NCRFs and RNN transducers.
Unified model for sequence labeling and classification.
problem Efficiently perform multiple sequence labeling tasks.
method Generative framework with shared natural language output space.
result Significant improvements in few-shot and low-resource slot labeling.
Locally-contextual CRFs improve sequence labeling performance.
problem Improving sequence labeling with contextual embeddings.
method Locally-contextual nonlinear CRFs using deep neural networks.
result Consistently outperforms linear chain CRF and previous state of the art.
Unified framework for generating set-valued outputs.
problem Handling unordered set outputs with varying sizes.
method Sequential Set Generation (SSG) framework.
result SSG outperforms baseline methods in experiments.
CTCModel extends Keras for transparent CTC classification.
problem Handling unsegmented input sequences with labels related to subsets of frames.
method Combines Keras and CTC implementation in Tensorflow backend.
result CTCModel predicts sequences of labels from unsegmented input.
Sum-product networks enhance sequence modeling with higher-order factors.
problem Modeling complex relations in sequence data with first-order models.
method Combining sum-product networks with higher-order linear-chain conditional random fields.
result Improved performance in sequence labeling tasks compared to state-of-the-art methods.
AC-RNN improves RNN for sequence labeling tasks.
problem RNN's exposure bias in maximum-likelihood training.
method Actor-Critic training for RNNs.
result AC-RNN outperforms CRF on NER and CCG tagging.
Paper proposes a new MLC framework without predefined label order, improving performance and generalization.
problem Exposure bias in multi-label classification due to lack of predefined label order.
method Proposes a new framework that transforms MLC into a sequence prediction problem without predefined label order.
result The proposed method outperforms competitive baselines and has better generalization capability.
The paper improves part-of-speech tagging with multi-task learning and character-level word representations.
problem Improving part-of-speech tagging accuracy.
method Developed a new character-level word representation using feedforward neural network, pretraining with existing word vectors, and an additional prediction of neighbour labels as an auxiliary loss.
result The methods significantly improved POS tagging performance on English and Russian languages.
Paper proposes semi-supervised learning using change points for sequence classification.
problem Limited labeled data for sequential sensor data classification.
method Change point detection for identifying class changes, semi-supervised learning with labeled and unlabeled data.
result Improved classification performance on human activity recognition datasets.
We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by usi…
Enhances sequence labeling with embedded-state latent CRFs.
problem Complex non-local constraints between sequence labels.
method Integrates multiple hidden states with low-rank log-potential scoring matrices.
result Model outperforms baseline CRF+RNN models with global constraints.
GIRNet tackles multi-tasking with mixed domain sequences, improving sentiment and tagging tasks.
problem Labeling sequences with mixed domain data and position-specific inference.
method Unified position-sensitive multi-task RNN architecture with gated state sequences from auxiliary data.
result GIRNet achieves new state-of-the-art performance in sentiment classification, POS tagging, and target position-sensitive annotation.
k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors model, which generate a sequence of labels, a sequence of out-of-sample feature vecto…
Paper uses user engagement signals to automatically label training data for AI assistants.
problem Lack of annotated training data for AI assistants.
method Leverages user engagement signals for unsupervised entity labeling and data augmentation.
result Significant accuracy gains in sequence labeling tasks and user-facing results.
SeqSleepNet tackles automatic sleep staging as a sequence-to-sequence problem.
problem Automatic sleep staging as a sequence-to-sequence classification problem.
method End-to-end hierarchical recurrent neural network (SeqSleepNet) with filterbank and attention-based recurrent layers.
result SeqSleepNet achieves high accuracy (87.1% overall accuracy, 83.3% macro F1-score, 0.815 Cohen's kappa) on a publicly available dataset.
The paper introduces uncertainty quantification for NER models.
problem Current NER models lack uncertainty measures, leading to downstream errors.
method Full-Sequence and Subsequence Conformal Prediction framework.
result The method provides formal guarantees about the reliability of model predictions.
Extracts main content from web pages using neural sequence labeling.
problem Lack of generalization in existing web page content extraction models.
method Neural sequence labeling model using HTML tags and words as input.
result Model outperforms state-of-the-art and adapts to changes in web page structure.
Generalized Earley parser predicts future events from sequence data.
problem Predicting future events from unsegmented, unlabeled sequence data.
method Integrates grammar parsing and classification for optimal segmentation and labels.
result Significantly outperforms other approaches in future human activity prediction.
This paper uses Bayesian networks to analyze label correlations for improving multi-label classifier chains.
problem Improving multi-label classifier chain performance by discovering label correlations and determining the label order.
method Bayesian network (BN) to model label correlations, scoring function to evaluate BN structure, heuristic algorithm to optimize BN, topological sorting to derive label order.
result The proposed BNCC method enhances multi-label classifier chain performance through optimized label order and correlation analysis.
Forest Fire Clustering discovers cell types from single-cell data.
problem Discovering cell types from large-scale single-cell sequencing data.
method Iterative label propagation and parallelized Monte Carlo simulation.
result Forest Fire Clustering outperforms state-of-the-art methods on diverse benchmarks.
Paper presents a neural network for recognizing human activities from unlabeled sensor data.
problem Time-consuming annotation of sensor data for activity recognition.
method Attention-based convolutional neural network for weakly labeled data.
result Attention model improves accuracy in recognizing human activities.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
A new algorithm detects changepoints in labeled and unlabeled data.
problem Accurate detection of abrupt changes in partially labeled data.
method Labeled Optimal Partitioning (LOPART) algorithm that fits train labels and predicts unlabeled changepoints.
result LOPART provides more accurate predictions than existing methods in both train and test sets.
SENSE enhances node sequences in graphs using vector embeddings.
problem Efficiently capturing graph node sequences for applications.
method SENSE-S learns node embeddings and composes them for sequences, preserving node order.
result SENSE-S increases multi-label classification and link-prediction accuracy by up to 50% and 78% respectively.
One of the fundamental tasks in understanding genomics is the problem of predicting Transcription Factor Binding Sites (TFBSs). With more than hundreds of Transcription Factors (TFs) as labels, genomic-sequence based TFBS prediction is a challenging multi-label classification task. There are two major biological mechan…
Framework transfers inertial motion across domains without labeled data.
problem Inertial measurements are sensitive to sensor placement and motion dynamics.
method Extracts domain-invariant features and transfers them to new domains.
result Framework converts raw IMU sequences into accurate inertial trajectories.
Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This manuscript presents Deep Convolutional Neural Fields (DeepCNF), a combination of DCNN with Conditional Random Field (CRF), for sequence labeling with highly imbalanced label distribution. The widely-us…
New techniques enforce sparseness in recurrent models, reducing memory usage.
problem Reducing memory usage in recurrent sequence models for NLP.
method Enforcing sparseness upfront in recurrent layers for language modeling and sequence labeling.
result Predefined sparseness leads to similar performance with fewer parameters.
The paper extends influence functions to sequence tagging tasks for better model interpretability.
problem Lack of interpretability methods for sequence tagging models.
method Define and compute influence of training instance segments on test segment predictions.
result The segment influence method tracks with true influence and identifies annotation errors.
Artificial neural networks (ANNs) have gained a well-deserved popularity among machine learning tools upon their recent successful applications in image- and sound processing and classification problems. ANNs have also been applied for predicting the family or function of a protein, knowing its residue sequence. Here w…
New method detects TC imagery patterns for rapid intensity change.
problem Detecting upcoming rapid intensity changes in TC satellite imagery.
method Nonparametric test of association between images and event labels using neural networks and bootstrap.
result Identifies archetypes of infrared imagery associated with elevated rapid intensification risk.
Paper presents a method to train NER models without labelled data using weak supervision.
problem Dealing with NER performance drop in new domains without labelled data.
method Weak supervision through automatic annotation and hidden Markov model integration.
result Improvement of about 7 percentage points in entity-level F1 scores. New method embeds DNA sequences for faster, more informative gene comparison.
problem Slow and costly sequence comparison methods for genes without exact matches.
method Recurrent neural networks to embed sequences in a low-dimensional space.
result Embedding allows for better comparison of genes without exact matches.
The paper improves generalization bounds for classifier chains with interdependent labels.
problem Improving generalization for classifier chains with multiple interdependent labels.
method Using large deviation inequalities for weakly dependent sequences, the paper derives a new generalization error bound.
result The derived bound explicitly shows dependencies between class labels and provides insights into the chain's order.
Contradiction graphs reveal VC dimension threshold.
problem Determining VC dimension of concept classes.
method Study contradiction graphs of binary concept classes.
result Single contradiction graph Gm(H) determines VC dimension. Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…
New PL method improves ASR accuracy without pseudo-labels.
problem Improving ASR accuracy with limited labeled data.
method End-to-end continuous pseudo-labeling with soft-labels.
result Soft-labels can lead to model collapse, but regularization can mitigate this.
GTI network learns linguistic features for multi-task sequence tagging.
problem Improving neural model performance on multi-task sequence tagging without explicit features.
method GTI network with neural gate modules to learn relations between tasks.
result GTI network outperforms baselines on chunking and NER tasks.
Hybrid model combines RNNs, encoders-decoders, and Transformers for sequence tasks.
problem Sequence labelling tasks
method Combination of bidirectional RNNs, encoder-decoder, and Transformer models
result Results are close to state-of-the-art and better for some tasks
Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work…
Dugong models multi-resolution weak supervision for sequential data.
problem Estimating unknown accuracies and correlations of weak supervision sources for sequential data.
method Dugong, a framework that models multi-resolution weak supervision sources with complex correlations, using parameter sharing to improve sample complexity.
result Dugong outperforms traditional supervision by 36.8 F1 points on clinician-validated labels for biomedical video repositories.
This study improves knowledge distillation for RNN-T models with noisy labels.
problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
We consider the problem of training input-output recurrent neural networks (RNN) for sequence labeling tasks. We propose a novel spectral approach for learning the network parameters. It is based on decomposition of the cross-moment tensor between the output and a non-linear transformation of the input, based on score …