The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant challenge in achieving accurate conversion from graph form …
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “neural sequence generation”
Investigates neural TTS systems for Japanese and English.
problem Improving neural TTS systems for high-quality speech synthesis.
method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.
result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.
NeSS combines neural and symbolic approaches for better compositional generalization.
problem Lack of compositional generalization in deep learning models.
method NeSS uses a neural network to generate traces, executed by a symbolic stack machine with sequence manipulation.
result Achieves 100% generalization performance across multiple domains.
We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine…
Enhances sequence memory capacity in neural networks.
problem Limited sequence capacity in Hopfield-like neural networks.
method Introducing a nonlinear interaction term and a generalized pseudoinverse rule.
result Significantly increased sequence capacity with novel scaling laws.
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…
Undirected neural sequence models such as BERT (Devlin et al., 2019) have received renewed interest due to their success on discriminative natural language understanding tasks such as question-answering and natural language inference. The problem of generating sequences directly from these models has received relativel…
Neural SDEs model continuous sequences using neural networks.
problem Modeling continuous-time dynamics in sequence data.
method Interprets time-series as samples from a continuous dynamical system, parameterized by Neural SDE.
result Demonstrates superior performance in diverse sequence modeling tasks.
A new method for fast graph embedding using diffusion graphs.
problem Efficiently generating graph embeddings for large networks.
method Diffusion graphs for rapid vertex sequence generation.
result Improved accuracy and performance with higher edge density.
Neural network optimizes learning sequence for reading words.
problem Children struggle with learning to read words due to inconsistent spelling-sound correspondences.
method Used a neural network to structure learning trials to optimize generalization accuracy.
result Significant improvement in generalization accuracy compared to random or frequency-based sequences.
This paper introduces a new neural ODE model for continuous-time sequence generation.
problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.
A new method optimizes neural sequence models for better task performance.
problem Training neural sequence models with maximum likelihood estimation ignores task losses.
method Maximum likelihood guided parameter search (MGS) in the parameter space.
result MGS optimizes sequence-level losses, reducing repetition and non-termination.
Neural networks struggle with long sequences, but a new method improves their performance.
problem Neural networks struggle to generalize to longer sequences and unseen data.
method Proposed a learned conditional masking mechanism and binary encoding for numbers.
result Models can now generalize far outside their training range with near-perfect accuracy.
Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context l…
Pointer Networksstat.ML
We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because th…
Knowledge extraction from the learning of sequences in a long short term memory (LSTM) architecturecs.LG
Method extracts knowledge from LSTM for sequence validation.
problem Validating sequences generated by unknown automata.
method Clustering hidden states to build a corresponding automaton.
result Automaton accurately predicts sequence validity.
Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the …
Deep Bayesian neural networks improve somatic variant calling accuracy.
problem Improving accuracy in pinpointing somatic variants from next-gen sequencing data.
method Deep Bayesian Recurrent Neural Networks (RNNs) for somatic variant calling.
result Deep Bayesian RNNs provide more reliable confidence intervals for variant calls.
System uses neural networks to prove program equivalence via rewrite rules.
problem Proving equivalence between two dataflow graphs.
method Developed a graph-to-sequence neural network trained on example generation to find semantics-preserving rewrite rules.
result System correctly outputs a rewrite sequence for 96% of program pairs, proving equivalence.
Develops a new point process model for detecting neural spike sequences.
problem Detecting sparse sequences of neural spikes in high-dimensional spike trains.
method A point process model that represents sequence occurrences as marked events in continuous time, with learnable time warping parameters.
result Demonstrates improved detection and modeling of neural spike sequences.
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.
Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learningeess.AS
Improves text-to-speech speed by interleaving character reading and audio synthesis.
problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.
The paper explores how to make neural networks extrapolate longer sequences.
problem Neural networks struggle to extrapolate beyond seen data, especially for longer sequences.
method The authors propose a model with separate content- and location-based attention mechanisms.
result Models with the proposed attention mechanisms are better at extrapolating longer sequences.
Meta-learning improves event prediction from short sequences.
problem Predicting events from short sequences is challenging.
method Meta-learning approach using recurrent neural networks and monotonic neural networks.
result Meta-learning enhances long-term prediction performance.
Graph Hawkes Neural Network forecasts evolving graph sequences.
problem Modeling dynamic graph sequences with complex event types.
method Generalized Hawkes process to neural network, capturing complex event impacts.
result Effective at predicting future events in evolving graph sequences.
Improved neural models for diverse user event sequences.
problem Challenges in modeling diverse user event sequences.
method Mixtures of latent embeddings with amortized variational inference.
result Systematic improvements over existing work for various predictive metrics.
In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and ge…
New model controls memory in seq2seq tasks, revealing learning regimes.
problem Understanding memory in seq2seq tasks using neural networks.
method Introducing a stochastic switching-Ornstein-Uhlenbeck (SSOU) model to control memory and a measure of non-Markovianity.
result Two learning regimes emerge from the interplay of time scales in the SSOU process.
FIGARO generates symbolic music with fine-grained control.
problem Minimal control over generated music sequences.
method Description-to-sequence task, learning conditional distribution of sequences given high-level descriptions.
result State-of-the-art controllable symbolic music generation.
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens. There are many ways to estimate or learn the …
Paper proposes using LSTM for LSH-based sequence alignment.
problem Sequence alignment using deep learning models.
method Deep bidirectional LSTM for feature learning and LSH-based sequence alignment.
result Higher accuracy achieved with LSTM-based model.
AI generates a sequence of death causes from hospital records.
problem Accurate death reporting for vital statistics and policy formulation.
method Neural machine translation models to generate causal chains, incorporating medical domain knowledge.
result Achieved 16.04 BLEU score for generating accurate causal chains.
New KNN test improves association analysis of high-dimensional sequencing data.
problem Challenges in using neural networks for high-dimensional sequencing data analysis.
method Kernel-based neural network (KNN) test for complex association analysis.
result KNN test outperforms SKAT in detecting non-linear and interaction effects.
This study mainly investigates two common decoding problems in neural keyphrase generation: sequence length bias and beam diversity. To tackle the problems, we introduce a beam search decoding strategy based on word-level and ngram-level reward function to constrain and refine Seq2Seq inference at test time. Results sh…
Thalamocortical motor circuit insights for more robust hierarchical control of complex sequencescs.LG
Model improves robustness of neural network sequences without transition failures.
problem Learning and generating complex sequences of motor primitives without interference.
method Inspired by thalamocortical circuit, uses specific module for motif transitions.
result Improved robustness of sequence generation with no transition failures.
Our team of dance artists, physicists, and machine learning researchers has collectively developed several original, configurable machine-learning tools to generate novel sequences of choreography as well as tunable variations on input choreographic sequences. We use recurrent neural network and autoencoder architectur…
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…
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…
Deep network predicts action sequences for complex tasks from a scene image.
problem Scalable task and motion planning from initial scene images.
method Deep convolutional recurrent neural network that predicts action sequences.
result Predicts promising action sequences, reducing motion planning problems.
Proposes OC4Seq for detecting anomalies in discrete event sequences.
problem Challenges in detecting anomalies in discrete event sequences, including data imbalance, discrete events, and sequential nature.
method Integrates anomaly detection with recurrent neural networks (RNNs) to embed sequences into latent spaces and designs a multi-scale RNN framework to capture multi-scale sequential patterns.
result OC4Seq consistently outperforms various baselines on three benchmark datasets.
MSLs use parallelizable root-finding for efficient ODE and PDE solutions.
problem Efficiently solving initial value problems for ODEs and PDEs.
method Leveraging time-parallel methods, MSLs use parallelizable root-finding algorithms.
result MSLs offer significant speedups in NFEs and inference time.
Benchmark for math reasoning models from human proofs.
problem Measuring and accelerating machine learning models in high-level mathematical reasoning.
method Built a non-synthetic dataset from theorem prover proofs, defined a task for model to fill in missing propositions, used hierarchical transformer to improve performance.
result Neural models can capture non-trivial mathematical reasoning, hierarchical transformer outperforms baseline.
Introduces alternators for modeling sequences, outperforming baselines.
problem Modeling complex sequential data with stability and efficiency.
method Two neural networks (OTN and FTN) alternate between outputting samples in observation and feature spaces, learned via cross-entropy criterion.
result Alternators outperform strong baselines in various domains (Lorenz equations, Neuroscience, Climate Science).
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, …
Recurrent Kernel Networksstat.ML
Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links between recurrent neural networks (RNNs) and substring kernels have recently been dra…
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.
GA-Net selectively attends to parts of a sequence for text classification.
problem Inefficient global attention mechanisms on long sequences.
method Gated Attention Network (GA-Net) using an auxiliary network to dynamically select and attend to important parts of the sequence.
result GA-Net achieves better performance with less computation and interpretability.
We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story,…