← Search

Vitalii Zhelezniak

2 accepted papers

2019

Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors

ICLR 2019poster

Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, when averaged word vectors are trained supervised on large corpora of paraphrases, they achieve state-of-the-art results o…

2018

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks

ICLR 2018workshop

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. Introducing the concept of an optimal representation space, we provide a simple theoretical resolution to this apparent paradox. In addition, we present a straightforward proced…

Cited by 8SourcecodeScholar