Congress with ISBN

Using External Knowledge to Improve Zero-shot Action Recognition in Egocentric Videos

Zero-shot learning is a very promising research topic. For a vision-based action recognition system, for instance, zero-shot learning allows to recognise actions never seen during the training phase. Previous works in zero-shot action recognition have exploited in several ways the visual appearance of input videos to infer actions. Here, we propose to add external knowledge to improve the performance of purely vision-based systems. Specifically, we have explored three different sources of knowledge in the form of text corpora.

A modular grammar-helping tool for Basque: work in progress

In this article, we explain the first steps to-wards a grammar-helping tool for Basquefrom a ruled-based approach. Specifically,we show the first steps carried out for help-ing with verb agreement, some of the dif-ficulties encountered, which linguistic is-sues arise when new rules are designed,and future perspectives

Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results than when using such data in isolation. In this work we analyse the impact that data translated with rule-based, phrase-based statistical and neural MT systems has on new MT systems.


Subscribe to RSS - Congress with ISBN