Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Neil Mallinar"'
Autor:
Tin Kam Ho, Yunfeng Zhang, Neil Mallinar, Robert L. Yates, Ayush Gupta, Rachel K. E. Bellamy, Ugrani Rajendra G, Abhishek Shah, Q. Vera Liao, Manikandan Gurusankar, Chris Desmarais, Blake McGregor
Publikováno v:
AAAI
Many conversational agents in the market today follow a standard bot development framework which requires training intent classifiers to recognize user input. The need to create a proper set of training examples is often the bottleneck in the develop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5748aa6b40341475cb7381f3eaba7b05
https://doi.org/10.1609/aaai.v33i01.33019528
https://doi.org/10.1609/aaai.v33i01.33019528
Publikováno v:
AAAI
Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data sets quickly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43edd770c07f95970a9895354a087260
Publikováno v:
EMNLP (1)
BERT-era question answering systems have recently achieved impressive performance on several question-answering (QA) tasks. These systems are based on representations that have been pre-trained on self-supervised tasks such as word masking and senten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a549899661655e4d92c3c86270483ed4
https://doi.org/10.18653/v1/2020.emnlp-main.87
https://doi.org/10.18653/v1/2020.emnlp-main.87
Probabilistic cross-identification has been successfully applied to a number of problems in astronomy from matching simple point sources to associating stars with unknown proper motions and even radio observations with realistic morphology. Here we s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74e92f4ee42c8ac96beb6d4b6487e250
Autor:
Mallinar, Neil, Rosset, Corbin
We examine Deep Canonically Correlated LSTMs as a way to learn nonlinear transformations of variable length sequences and embed them into a correlated, fixed dimensional space. We use LSTMs to transform multi-view time-series data non-linearly while
Externí odkaz:
http://arxiv.org/abs/1801.05407
Most data scientists and engineers today rely on quality labeled data to train machine learning models. But building a training set manually is time-consuming and expensive, leaving many companies with unfinished ML projects. There's a more practical