As pointed out before, to find a proper starting state, and simulate the Gibbs sampler for a k-DPPs, we need to have access to CD(i,1) (0≤k−1) sampling oracles of the kernel. In this section, we study the problem for Gaussian kernels, and as a speci…

lstmacl15 presented stack LSTMs and used them to implement a transition-based dependency parser. The parser uses a greedy learning strategy which potentially provides very high parsing speed while still achieving state-of-the-art results. We have de…

The k-local Hamiltonian problem is QMA-complete for k≥2 (it is trivially in P when k=1) and it is still an open question whether the general commuting Hamiltonian is in NP (and hence NP-complete). Here we restricted ourselves to the case that when t…

Identifying domain-adjacent instances is a practical issue that can improve downstream semantic parsing precision, and thus provide a smoother and more reliable user experience. In this paper, we formalize this task, and introduce a novel sentence e…

In this short note, we introduced the notion of norm subGaussian random vectors, which include subGaussian random vectors and bounded random vectors as special cases. While it is true that subGaussian(σ√d)⊆nSG(σ)⊆subGaussian(σ), applying concentrati…

In this paper, we run a series of prediction tasks on the internal representations of deep NLP models, and find these RNNs are able to induce syntax without explicit linguistic supervision. We also observe that the representations taken from deeper …