Reno Kriz

TL;DR: This article presented a survey of decoding-time strategies for generating diverse outputs from a conditional language model, where over-sample candidates, then use clustering to remove similar sequences, thus achieving high diversity without sacrificing quality.

TL;DR: The authors incorporate content word complexities, as predicted with a leveled word complexity model, into the loss function during training and generate a large set of diverse candidate simplifications at test time, and rerank these to promote fluency, adequacy, and simplicity.

TL;DR: This paper explored several methods for characterizing speech changes in schizophrenia spectrum disorders (SSD) compared to healthy control (HC) participants and approached linguistic phenotyping on three levels: individual words, parts-of-speech (POS), and sentence-level coherence.

TL;DR: This work performs an extensive survey of decoding-time strategies for generating diverse outputs from a conditional language model, and presents a novel method where over-sample candidates, then use clustering to remove similar sequences, thus achieving high diversity without sacrificing quality.

TL;DR: A novel method of predicting word concreteness from images is introduced, which improves on a previous state-of-the-art unsupervised technique and allows us to predict when image-based translation may be effective, enabling consistent improvements to a state of theart text-based word translation system.