RollerS. x 5

bookRéférences 5

Références · 2022-01-01

Opt: Open pre-trained transformer language models

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

ZhangS.ChenM.RollerS.GoyalN.ArtetxeM.

Références · 2020-01-01

Adding chit-chat to enhance task-oriented dialogues

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

RollerS.SunK.MoonS.CrookP.SilvertB.

Références · 2016-03-03

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...

ZhangY.RollerS.WallaceB.

Références · 2011-01-01

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...

RollerS.DominguezM.YoungR.M.

Références

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