RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-...
Inference-time adaptation methods for semantic parsing are useful for
le...
Text-to-SQL parsers typically struggle with databases unseen during the ...
Despite cross-lingual generalization demonstrated by pre-trained multili...
Online alignment in machine translation refers to the task of aligning a...
Pre-trained multilingual language models such as mBERT and XLM-R have
de...
RNN-Transducer (RNN-T) models have become synonymous with streaming
end-...
Long range forecasts are the starting point of many decision support sys...
We consider the problem of training a classification model with group
an...
In several real world applications, machine learning models are deployed...
Our goal is to evaluate the accuracy of a black-box classification model...
Recent research in multilingual language models (LM) has demonstrated th...
Given two large lists of records, the task in entity resolution (ER) is ...
We consider the task of personalizing ASR models while being constrained...
We present DeepMVI, a deep learning method for missing value imputation ...
In recent years, marked temporal point processes (MTPPs) have emerged as...
State-of-the-art NLP inference uses enormous neural architectures and mo...
We evaluate named entity representations of BERT-based NLP models by
inv...
We introduce the problem of adapting a black-box, cloud-based ASR system...
In many applications labeled data is not readily available, and needs to...
Domain generalization refers to the task of training a model which
gener...
Scarcity of labeled data is a bottleneck for supervised learning models....
We present a Parallel Iterative Edit (PIE) model for the problem of loca...
We present ARU, an Adaptive Recurrent Unit for streaming adaptation of d...
Given a small corpus D_T pertaining to a limited set of focused
topics,...
We study the calibration of several state of the art neural machine
tran...
We present CROSSGRAD, a method to use multi-domain training data to lear...
Accurate demand forecasts can help on-line retail organizations better p...
Augmenting a neural network with memory that can grow without growing th...
Encoder-decoder networks are popular for modeling sequences probabilisti...
The problem of collecting reliable estimates of occurrence of entities o...
We consider the problem of jointly training structured models for extrac...
Collective graphical models exploit inter-instance associative dependenc...