Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Uthus, David"'
Historically, sign language machine translation has been posed as a sentence-level task: datasets consisting of continuous narratives are chopped up and presented to the model as isolated clips. In this work, we explore the limitations of this task f
Externí odkaz:
http://arxiv.org/abs/2406.11049
Autor:
Santos, Cicero Nogueira dos, Lee-Thorp, James, Noble, Isaac, Chang, Chung-Ching, Uthus, David
Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing model size proportionally increases the model's computation footprint. In this work, we seek to aggress
Externí odkaz:
http://arxiv.org/abs/2311.10768
Machine learning for sign languages is bottlenecked by data. In this paper, we present YouTube-ASL, a large-scale, open-domain corpus of American Sign Language (ASL) videos and accompanying English captions drawn from YouTube. With ~1000 hours of vid
Externí odkaz:
http://arxiv.org/abs/2306.15162
We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pr
Externí odkaz:
http://arxiv.org/abs/2305.11129
Autor:
Ainslie, Joshua, Lei, Tao, de Jong, Michiel, Ontañón, Santiago, Brahma, Siddhartha, Zemlyanskiy, Yury, Uthus, David, Guo, Mandy, Lee-Thorp, James, Tay, Yi, Sung, Yun-Hsuan, Sanghai, Sumit
Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but also from applying feedforward and projection layers to every token. H
Externí odkaz:
http://arxiv.org/abs/2303.09752
Autor:
Uthus, David, Ni, Jianmo
Evaluating automatically-generated text summaries is a challenging task. While there have been many interesting approaches, they still fall short of human evaluations. We present RISE, a new approach for evaluating summaries by leveraging techniques
Externí odkaz:
http://arxiv.org/abs/2212.08775
Autor:
Guo, Mandy, Ainslie, Joshua, Uthus, David, Ontanon, Santiago, Ni, Jianmo, Sung, Yun-Hsuan, Yang, Yinfei
Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present a new model, called LongT5, with which we explore the effects of
Externí odkaz:
http://arxiv.org/abs/2112.07916
We describe Verse by Verse, our experiment in augmenting the creative process of writing poetry with an AI. We have created a group of AI poets, styled after various American classic poets, that are able to offer as suggestions generated lines of ver
Externí odkaz:
http://arxiv.org/abs/2103.17205
Autor:
Sheng, Emily, Uthus, David
There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative language applications are meant for d
Externí odkaz:
http://arxiv.org/abs/2011.02686
We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjac
Externí odkaz:
http://arxiv.org/abs/2010.03802