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.
Seq2seq ASR adapts to speakers, improving performance by 25%.
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…
Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities. The central challenge in multimodal learning involves learning representations that can process and relate information from multiple modalities. In this paper, we propose two methods for unsupervised learning of j…
Neural machine translation used to convert CUDA to OpenCL.
Seq2Seq models speed up epidemic model predictions.
In this work, sequence-to-sequence (seq2seq) models, originally developed for language translation, are used to predict the temporal evolution of complex, multi-physics computer simulations. The predictive performance of seq2seq models is compared to state transition models for datasets generated with multi-physics cod…
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.
Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convol…
Method uses Seq2Seq learning to automatically generate recovery commands for ICT systems.
In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text conversion, and image caption generation. The underlying framework for all these…
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Seque…
Seq2Seq models perform well in generating If-Then programs from natural language.
New model controls memory in seq2seq tasks, revealing learning regimes.
Paper proposes a new neural machine translation method for wave data.
Improves spatio-temporal forecasting by reducing errors between training and inference.
Information extraction and user intention identification are central topics in modern query understanding and recommendation systems. In this paper, we propose DeepProbe, a generic information-directed interaction framework which is built around an attention-based sequence to sequence (seq2seq) recurrent neural network…
Models learn to transform musical scores into expressive performances.
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 …
The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In this contribution, we analyse an attention-based seq2seq speech recognition syste…
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 method embeds RNN Seq2Seq models to visualize spatiotemporal data.
In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating on the prediction of clinically relevant outcomes, we show that in a practical …
New techniques improve channel prediction in noisy wireless systems.
A new approach to distill unnormalized EBM for energy-based seq2seq models.
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently repre…
Proposes models to generate more interesting story endings.
In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such a…
Neural networks learn symbolic structure to perform compositional tasks.
GAMs combine autoregressive and log-linear components for data-efficient sequence learning.
Unsupervised model detects healthcare fraud from patient visit data.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech…
This paper uses a diffusion model to forecast electrical loads with uncertainty.
This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling such as speech synthesis and recognition, machine translation, and image captioni…
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
Single layer Feedforward Neural Network(FNN) is used many a time as a last layer in models such as seq2seq or could be a simple RNN network. The importance of such layer is to transform the output to our required dimensions. When it comes to weights and biases initialization, there is no such specific technique that co…
This study evaluates the performances of an LSTM network for detecting and extracting the intent and content of com- mands for a financial chatbot. It presents two techniques, sequence to sequence learning and Multi-Task Learning, which might improve on the previous task.
BPE improves text-to-SQL generation by reducing training time and improving accuracy.
In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to a multi-turn dialogue scenario by modifying the state-of-the-art hredGAN architecture to simultaneously capture utterance attributes such as speaker identity, dialogue topic, speaker sentiments and so on. The …
A new framework improves ASR alignment accuracy via optimal transport.
Modeling latent dynamics in high-dimensional event sequences without prior knowledge.
A new transformer model corrects diacritics and typos in multiple languages.
Deep learning model predicts traffic flows across entire network for multiple steps ahead.
Improved text summarization using neural semantic encoders with hierarchical structure.
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily generalize in this way, e.g. by applying known grammatical rules to novel words.…
Boosted embeddings improve time series forecasting models.
Improved neural keyphrase generation by beam search with reward functions.