deepSA2018 at SemEval-2018 Task 1: Multi-task Learning of Different Label for Affect in Tweets

no code implementations • SEMEVAL 2018 • Zi-Yuan Gao, Chia-Ping Chen

These classification models are trained sequentially to learn different features for different classification tasks.

Classification General Classification +2

Preference-based Teaching

no code implementations • 6 Feb 2017 • Zi-Yuan Gao, Christoph Ries, Hans Ulrich Simon, Sandra Zilles

We introduce a new model of teaching named "preference-based teaching" and a corresponding complexity parameter---the preference-based teaching dimension (PBTD)---representing the worst-case number of examples needed to teach any concept in a given concept class.

Combining Models of Approximation with Partial Learning

no code implementations • 5 Jul 2015 • Zi-Yuan Gao, Frank Stephan, Sandra Zilles

Here three variants of approximate learning will be introduced and investigated with respect to the question whether they can be combined with partial learning.

Object