RollerS. x 5

bookRéférences 5

Opt: Open pre-trained transformer language models

… To understand the potential harm of OPT-175B, we evaluate a series of benchmarks relate...

2022-01-01 00:00:00

ZhangS.ChenM.RollerS.GoyalN.ArtetxeM.

Adding chit-chat to enhance task-oriented dialogues

… have positive sentiment, measured by VADER, a lexicon and rule-based sentiment analysis...

2020-01-01 00:00:00

RollerS.SunK.MoonS.CrookP.SilvertB.

MGNC-CNN: A simple approach to exploiting multiple word embeddings for sentence classification

We introduce a novel, simple convolution neural network (CNN) architecture - multi-group norm constr...

2016-03-03 00:00:00

ZhangY.RollerS.WallaceB.

Design and evaluation of afterthought, a system that automatically creates highlight cinematics for 3D games

… One primary difference may be that in a live-action film, an actor’s face can...

2011-01-01 00:00:00

RollerS.DominguezM.YoungR.M.

The (un) expected effects of applying standard cleansing models to human ratings on compositionality

… While this may be a happy coincidence, it does seem to suggest that the ideal minimum s...

RollerS.WaldeSSimScheibleS.

Mots-clés associés