Zobrazeno 1 - 10
of 43
pro vyhledávání: '"Fernandez, Roland"'
Large Language Models (LLMs) have demonstrated impressive abilities in symbol processing through in-context learning (ICL). This success flies in the face of decades of predictions that artificial neural networks cannot master abstract symbol manipul
Externí odkaz:
http://arxiv.org/abs/2410.17498
Autor:
Deng, Yuntian, Prasad, Kiran, Fernandez, Roland, Smolensky, Paul, Chaudhary, Vishrav, Shieber, Stuart
To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason effectively, it
Externí odkaz:
http://arxiv.org/abs/2311.01460
Autor:
Soulos, Paul, Hu, Edward, McCurdy, Kate, Chen, Yunmo, Fernandez, Roland, Smolensky, Paul, Gao, Jianfeng
In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. To facilitate the learning of these symbolic sequences, we introduce a
Externí odkaz:
http://arxiv.org/abs/2306.00751
Autor:
Soulos, Paul, Rao, Sudha, Smith, Caitlin, Rosen, Eric, Celikyilmaz, Asli, McCoy, R. Thomas, Jiang, Yichen, Haley, Coleman, Fernandez, Roland, Palangi, Hamid, Gao, Jianfeng, Smolensky, Paul
Publikováno v:
Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens.
Externí odkaz:
http://arxiv.org/abs/2208.06061
What explains the dramatic progress from 20th-century to 21st-century AI, and how can the remaining limitations of current AI be overcome? The widely accepted narrative attributes this progress to massive increases in the quantity of computational an
Externí odkaz:
http://arxiv.org/abs/2205.01128
Autor:
Jiang, Yichen, Celikyilmaz, Asli, Smolensky, Paul, Soulos, Paul, Rao, Sudha, Palangi, Hamid, Fernandez, Roland, Smith, Caitlin, Bansal, Mohit, Gao, Jianfeng
Abstractive summarization, the task of generating a concise summary of input documents, requires: (1) reasoning over the source document to determine the salient pieces of information scattered across the long document, and (2) composing a cohesive t
Externí odkaz:
http://arxiv.org/abs/2106.01317
Autor:
Russin, Jacob, Fernandez, Roland, Palangi, Hamid, Rosen, Eric, Jojic, Nebojsa, Smolensky, Paul, Gao, Jianfeng
A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations (e.g., audito
Externí odkaz:
http://arxiv.org/abs/2105.08961
Autor:
Akbari, Hassan, Palangi, Hamid, Yang, Jianwei, Rao, Sudha, Celikyilmaz, Asli, Fernandez, Roland, Smolensky, Paul, Gao, Jianfeng, Chang, Shih-Fu
Neuro-symbolic representations have proved effective in learning structure information in vision and language. In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning. Our approa
Externí odkaz:
http://arxiv.org/abs/2011.09530
Performing diagnosis or exploratory analysis during the training of deep learning models is challenging but often necessary for making a sequence of decisions guided by the incremental observations. Currently available systems for this purpose are li
Externí odkaz:
http://arxiv.org/abs/2001.01215
Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences. Inspired by this trend, we study the question of how Transformer-based models can improve the performance o
Externí odkaz:
http://arxiv.org/abs/1911.07141