Deep Learning of Grammatically-Interpretable Representations Through Question-Answering

18 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.

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving (2019, background): “…to enable the fully distributed representation of symbolic structure (like a hierarchy of features) which has recently resurfaced as an important direction for neural network research (Lake & Baroni, 2017; Bahdanau et al., 2018; van Steenkiste et al., 2019; Palangi et al., 2017; Tang et al., 2018).”
A Simple Recurrent Unit with Reduced Tensor Product Representations (2018, background): “, 2016) was addressed (Palangi et al., 2017) with an LSTM with hidden state given by a single TPR binding; the present work deploys complexes containing multiple bindings (albeit reduced ones).”
Learning Distributed Representations of Symbolic Structure Using Binding and Unbinding Operations (2018, background): “Question-answering on SQuAD 68 [33] was addressed [26] with a gated recurrent unit in which the hidden state was a single TPR binding; 69 the present work deploys complexes containing multiple bindings.”
Learning to Reason with Third-Order Tensor Products (2018, methodology): “However, previous work used TPRs of order 2 for simpler associations in the context of image-caption generation [35], question-answering [36], and general NLP [37] problems with a gradient-based optimizer similar to ours.”