Language modeling with sum-product networks

83 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling (2016, background): “We list in Table 3 (Cheng et al., 2014) 5M - 100.0 LSTM (medium) (Zaremba et al., 2014) 6.4 Q UALITATIVE R ESULTS One important feature of our framework that leads to better word predictions is the explicit mechanism to assign probabilities to words not merely according to the observed output…”
Character-Aware Neural Language Models (2015, methodology): “2010), sum-product (Cheng et al. 2014), log-bilinear (Mnih and Hinton 2007), and convolutional (Wang et al.”
Online and Distributed Bayesian Moment Matching for Parameter Learning in Sum-Product Networks (2016, methodology): “SPNs have been used in image completion tasks [Poon and Domingos, 2011], activity recognition [Amer and Todorovic, 2012, Amer and Todorovic, 2015], speech modeling [Peharz et al., 2014b] and language modeling [Cheng et al., 2014].”
Faster Attend-Infer-Repeat with Tractable Probabilistic Models (2019, methodology): “, 2017), which has been successfully applied in tasks like image recognition (Gens & Domingos, 2012), language modeling (Cheng et al., 2014), speech processing (Peharz et al.”
Online Algorithms for Sum-Product Networks with Continuous Variables (2016, unknown): “Based on those advantages, SPNs have been used in many applications including image completion (Poon and Domingos, 2011), speech modeling (Peharz et al., 2014) and language modeling (Cheng et al., 2014).”