Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

3875113150 · Jun 202019922001200920182026
48 results for sequence summarization

A new model improves text summarization by integrating topic information.

problem Improving the coherence, diversity, and informativeness of text summarization.
method Integrates topic information into ConvS2S model and uses SCST for optimization.
result The proposed model outperforms state-of-the-art methods in abstractive summarization.

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.

Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options. Such lists are often evaluated using submodular reward functions that measure both quality and diversity. We propose a simple, efficient, and provably near-optim…

2013-05-11abs ↗pdf ↗

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.

Method summarizes and predicts time series data for COVID-19 cases and deaths.

problem Summarizing and predicting time series data for multiple related time series.
method Hierarchical algorithm generating shapelets for centroids, nearest neighbor search for labeling, dynamic time warping for non-uniform lengths.
result Predictive model for individual time series based on aggregated statistics.

New method uses dendrograms for better mixture model selection and clustering.

problem Selecting the correct number of components in finite mixture models.
method Hierarchical clustering tree derived from overfitted latent mixing measures.
result Consistently selects the true number of mixing components and optimal convergence rate for parameter estimation.

This work improves sequence-to-sequence models using amortized variational inference for context vectors.

problem Improving the performance of sequence-to-sequence models, especially in hard tasks like document summarization and video captioning.
method The approach treats context vectors as latent variables and infers their posteriors using an approximate finite mixture model via amortized variational inference.
result The method yields stronger generalization capacity and improved effectiveness over state-of-the-art alternatives.

Generative Bridging Network improves sequence prediction models by penalizing confidence and smoothing language.

problem Data sparsity and overfitting in sequence prediction tasks.
method Introduces a bridge module to extend ground truth and minimize KL-divergence between bridge distribution and generator.
result Significant improvements over strong baselines in machine translation and text summarization tasks.

We give an overview of how calculus of the embedding functor can be used for the study of long knots and summarize various results connecting the calculus approach to the rational homotopy type of spaces of long knots, collapse of the Vassiliev spectral sequence, Hochschild homology of the Poisson operad, finite type k…

2006-01-12abs ↗pdf ↗

Set-Sequence model learns cross-sectional dynamics directly from time series data.

problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.

Future autonomous systems need reliable world models and complex action sequences.

problem Current automated systems lack reliable world models and complex action sequences.
method Introduce energy-based and latent variable models combined in a hierarchical joint embedding predictive architecture (H-JEPA).
result Combining energy-based and latent variable models in H-JEPA can lead to reliable world models and complex action sequences.

New L2D framework allows deferring specific parts of a sequence prediction to experts.

problem Current L2D methods defer entire predictions, which is not ideal for long sequences.
method Proposes token-level and one-time rejectors to defer specific outputs of a model prediction to experts.
result Granular deferrals achieve better cost-accuracy tradeoffs than whole deferrals.

TREP learns pedestrian trajectories efficiently without needing full datasets.

problem Learning fixed-length vector representations of variable-length trajectories.
method Actor-critic sequence-to-sequence autoencoder with spatial-aware objective function.
result TREP efficiently learns trajectory representations without needing full datasets.

Unified framework connects various sequence prediction algorithms.

problem Compounding error and poor exploration efficiency in sequence prediction models.
method Formal connection between algorithms through a generalized entropy regularized policy optimization formulation.
result Unified interpretation offers systematic view of varying properties of exploration and learning efficiency.

Solution for voice conversion with limited data using hierarchical seq2seq and attention models.

problem Voice conversion between speakers with limited parallel audio pairs.
method Hierarchical sequence to sequence model with attention-based decoder, trained on single speaker dataset.
result Improved voice conversion quality using mel spectrograms and wavenet vocoder.

Sequence-to-sequence models predict resource usage for co-scheduled jobs in data centers.

problem Challenges in co-scheduling jobs due to resource interference and inefficiencies.
method Sequence-to-sequence models based on recurrent neural networks for workload interference prediction.
result Models accurately forecast resource usage trends from job profiles, improving scheduling decisions.

This study improves text summarization and fake news detection using neural models.

problem Improving text summarization and detecting fake news.
method Exploring and comparing different neural models for text summarization, including LSTM-encoder-decoder, pointer-generator networks, and transformers. Applying these models as a feature extractor for fake news detection.
result The proposed neural models enhance text summarization and improve fake news detection accuracy.

BART pretrains sequence-to-sequence models by corrupting text and reconstructing it.

problem Improving natural language generation, translation, and comprehension.
method BART uses a denoising autoencoder trained on a Transformer architecture with various noising techniques.
result BART achieves state-of-the-art performance on various NLP tasks with minimal training resources.

Improved text summarization using belief propagation on weighted bipartite graphs.

problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.

We introduce Courant algebroids, providing definitions, some historical notes, and some elementary properties. Next, we summarize basic properties of graded manifolds. Then, drawing on the work of Roytenberg and others, we introduce the graded or supergraded language demonstrating a cochain complex / cohomology for (ge…

2010-04-09abs ↗pdf ↗

Mathematical framework for language models processes text and predicts next tokens.

problem Understanding and optimizing the performance of large language models.
method Describes encoding, prediction models, learning from data, and deployment of LLMs.
result Demonstrates remarkable empirical successes and provides a platform for further research.

Improves document summarization by combining word embeddings and n-grams.

problem Exact word matching fails to measure semantic similarity between sentences.
method Uses deep embedding features and tf-idf features to improve sentence similarity measure; builds an improved sentence similarity graph; employs a submodular objective function; develops a Transformer-based compression model.
result Outperforms tf-idf based approach and achieves state-of-the-art performance on DUC04 dataset.

Compact Recurrent Transformer (CRT) improves Transformer efficiency for long sequences.

problem Efficiently scaling Transformer architecture to long sequences with limited compute resources.
method Combines shallow Transformer models with recurrent neural networks and persistent memory.
result CRT achieves comparable or superior performance to full-length Transformers with shorter segments and reduced FLOPs.

This work tackles extractive compression by formulating it as tree transduction.

problem Extractive compression as a challenging natural language processing problem.
method Formulated as a parse tree transduction problem, using a deep neural model with Long Short-Term Memory extended to consider parent-child relationships.
result Achieves state-of-the-art performance on sentence compression benchmarks.

Survey of machine learning methods for spatiotemporal sequence forecasting.

problem Forecasting multi-step future of spatiotemporal systems based on past observations.
method Defined STSF problem, classified into subcategories, identified challenges, reviewed existing methods.
result No unified perspective on machine learning for STSF previously existed.