Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Nazneen Fatema"'
Publikováno v:
SAGE Open, Vol 14 (2024)
The environmental impact of trade openness has been a subject of extensive research, but gaps exist in understanding how green financing interact with trade openness on carbon emissions in emerging economies. Thus, this research aims to investigate t
Externí odkaz:
https://doaj.org/article/357981a556e4442da6f3eb3254060062
Autor:
Choubey, Prafulla Kumar, Fabbri, Alexander R., Vig, Jesse, Wu, Chien-Sheng, Liu, Wenhao, Rajani, Nazneen Fatema
Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter Ensembling
Externí odkaz:
http://arxiv.org/abs/2110.07166
Summarization systems make numerous "decisions" about summary properties during inference, e.g. degree of copying, specificity and length of outputs, etc. However, these are implicitly encoded within model parameters and specific styles cannot be enf
Externí odkaz:
http://arxiv.org/abs/2110.04400
Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization. However, due to the black-box nature of neural models, uninformative e
Externí odkaz:
http://arxiv.org/abs/2104.07605
Influence functions approximate the "influences" of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model and training data size. We present
Externí odkaz:
http://arxiv.org/abs/2012.15781
For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield useful re
Externí odkaz:
http://arxiv.org/abs/2012.00195
Autor:
Rajani, Nazneen Fatema, Krause, Ben, Yin, Wengpeng, Niu, Tong, Socher, Richard, Xiong, Caiming
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose using k nearest neighbor (kNN) representations to identify training e
Externí odkaz:
http://arxiv.org/abs/2010.09030
Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner. Here we develop an inverse problem formulation to deconstruc
Externí odkaz:
http://arxiv.org/abs/2010.07126
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison. A good review needs to be knowledgeable, namely that the comment
Externí odkaz:
http://arxiv.org/abs/2010.06119
A standard way to address different NLP problems is by first constructing a problem-specific dataset, then building a model to fit this dataset. To build the ultimate artificial intelligence, we desire a single machine that can handle diverse new pro
Externí odkaz:
http://arxiv.org/abs/2010.02584