Telecom

A system to produce context-aware captions for news images

Computer systems that can automatically generate image captions have been around for several years. While many of these techniques perform considerably well, the captions they produce are typically generic and somewhat uninteresting, ...

Machine learning & AI

A new approach for unsupervised paraphrasing without translation

In recent years, researchers have been trying to develop methods for automatic paraphrasing, which essentially entails the automated abstraction of semantic content from text. So far, approaches that rely on machine translation ...

Computer Sciences

Using multi-task learning for low-latency speech translation

Researchers from the Karlsruhe Institute of Technology (KIT), in Germany, have recently applied multi-task machine learning to low-latency neural speech translation. Their study, which was pre-published on ArXiv, addresses ...

Computer Sciences

Bible helps researchers perfect translation algorithms

In search of inspiration for improving computer-based text translators, researchers at Dartmouth College turned to the Bible for guidance. The result is an algorithm trained on various versions of the sacred texts that can ...

Computer Sciences

Neural network trained to properly name organic molecules

Skoltech researchers and their colleagues from Lomonosov Moscow State University and the Syntelly start-up have developed and trained a neural network to generate names for organic compounds in accordance with the IUPAC nomenclature ...

Computer Sciences

Facebook enhances AI computer vision with SEER

At a time when many versions of AI rely on pre-established data sets for image recognition, Facebook has developed SEER (Self-supERvised) – a deep learning solution able to register images on the Internet independent of ...

page 1 from 2