arXiv research

Chatbot uses BERT to handle financial investment questions, improving accuracy and decision-making.

A transformer model improves spell correction with hierarchical attention.

We present a novel language adaptable spell checking system which detects spelling errors and suggests context sensitive corrections in real-time. We show that our system can be extended to new languages with minimal language-specific processing. Available literature majorly discusses spell checkers for English but the…

A new transformer model corrects diacritics and typos in multiple languages.

This study analyses the duration dependence of events that trigger volatility persistence in stock markets. Such events, in our context, are monthly spells of contiguous price decline or negative returns for the S&P500 stock market index over the last 145 years. Factors known to affect the duration of these spells are …

In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Lis…

We further study the incidence relations that arise from the various subtowers, known as Baby Monster, which exist within the $\mathbb{R}^{3}$-Monster Tower. This allows us to complete the $RVT$ class spelling rules. We also present a method of calculating the various Baby Monster that appear within the Monster Tower.

The P300 Brain-Computer Interface (BCI) is a well-established communication channel for severely disabled people. The P300 event-related potential is mostly characterized by its amplitude or its area, which correlate with the spelling accuracy of the P300 speller. Here, we introduce a novel approach for estimating the …

We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by applying subword models such as byte-pair encoding (BPE) and character-level encoders, but these methods are highly sensitive to spelling mistake…

A method makes particle filters differentiable without altering their forward pass.

AV-ASR system improves speech recognition with visual context.

We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihoo…

Grapheme-based acoustic modeling has recently been shown to outperform phoneme-based approaches in both hybrid and end-to-end automatic speech recognition (ASR), even on non-phonemic languages like English. However, graphemic ASR still has problems with rare long-tail words that do not follow the standard spelling conv…

We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent ne…

Modern e-commerce catalogs contain millions of references, associated with textual and visual information that is of paramount importance for the products to be found via search or browsing. Of particular significance is the book category, where the author name(s) field poses a significant challenge. Indeed, books writ…

We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. …

Improves ASR accuracy for domain mismatch using machine translation.

Winterization of Texas power system profitable but risky, estimated at $11.74bn over 30 years.

Improves diversity of text-to-image models without sacrificing FID.

Study shows AD for neural nets with machine-representable numbers can be incorrect.

While computer and communication technologies have provided effective means to scale up many aspects of education, the submission and grading of assessments such as homework assignments and tests remains a weak link. In this paper, we study the problem of automatically grading the kinds of open response mathematical qu…

The Monster tower, also known as the Semple tower, is a sequence of manifolds with distributions of interest to both differential and algebraic geometers. Each manifold is a projective bundle over the previous. Moreover, each level is a fiber compactified jet bundle equipped with an action of finite jets of the diffeom…

Paper proposes an efficient method for bounding box annotation in object detection.

Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectl…

We review (non-abelian) extensions of a given Lie algebra, identify a 3-dimensional cohomological obstruction to the existence of extensions. A striking analogy to the setting of covariant exterior derivatives, curvature, and the Bianchi identity in differential geometry is spelled out. In the new version references ad…

We propose a novel algorithm for efficiently computing a sparse directed adjacency matrix from a group of time series following a causal graph process. Our solution is scalable for both dense and sparse graphs and automatically selects the LASSO coefficient to obtain an appropriate number of edges in the adjacency matr…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network. In previous work, we have shown that such architectures are comparable to stat…

This work introduces a protocol to automatically select the correct range of scales for meaningful Intrinsic Dimension estimation.

Deep Autotuner corrects singing pitch using neural networks.

Direct acoustics-to-word (A2W) models in the end-to-end paradigm have received increasing attention compared to conventional sub-word based automatic speech recognition models using phones, characters, or context-dependent hidden Markov model states. This is because A2W models recognize words from speech without any de…

New SGD algorithm finds critical points faster with second-order corrections.

Paper analyzes convergence of PAM method for low-rank factorization models.

We describe a machine-learning approach to pitch correcting a solo singing performance in a karaoke setting, where the solo voice and accompaniment are on separate tracks. The proposed approach addresses the situation where no musical score of the vocals nor the accompaniment exists: It predicts the amount of correctio…

Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…

The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genetic algorithms have been used successfully for many problems, one criticism is that hand-crafting its fitness function, the test that aims to…

The recent use of `Big Code' with state-of-the-art deep learning methods offers promising avenues to ease program source code writing and correction. As a first step towards automatic code repair, we implemented a graph neural network model that predicts token types for Javascript programs. The predictions achieve an a…

This paper presents an automated supervised method for Persian wordnet construction. Using a Persian corpus and a bi-lingual dictionary, the initial links between Persian words and Princeton WordNet synsets have been generated. These links will be discriminated later as correct or incorrect by employing seven features …

STAS selects optimal spatio-temporal scales for bias correction in precipitation forecasts.

Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the huma…

ProSelfLC improves robustness of deep neural networks by automatically deciding trust in predictions.

Approximate Bayesian Computation (ABC) is a framework for performing likelihood-free posterior inference for simulation models. Stochastic Variational inference (SVI) is an appealing alternative to the inefficient sampling approaches commonly used in ABC. However, SVI is highly sensitive to the variance of the gradient…

TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.

Study proposes a new method to estimate bias-correction term for ATE estimation.

Paper stabilizes generative model training with synthetic data.

Corrects errors in ILA for Bayesian inference in LGMs.

A new model cleans vocal note event annotations in music.

Deep learning is also known as hierarchical learning, where the learner _learns_ to represent a complicated target function by decomposing it into a sequence of simpler functions to reduce sample and time complexity. This paper formally analyzes how multi-layer neural networks can perform such hierarchical learning _ef…

New method for estimating treatment effects without complex propensity models.