Генератор

Starting from the assumption that machine translation (MT) should be based on theoretically sound grounds, we argue that, given the state of the art, the only viable solution for the …...

We describe a system of reversible grammar in which, given a logic-grammar specification of a natural language, two efficient PROLOG programs are derived by an off-line compilation process: a parser …...

We propose a model based on context en- coder to solve formal analogies on strings like aaabbbccc : aaaabbbbcccc :: abc : x ⇒ x = aabbcc or ubid : …...

AbstractThis paper proposes an approach for applying GANs to NMT. We build a conditional sequence generative adversarial net which comprises of two adversarial sub models, a generator and a discriminator. …...

AbstractRecent work has shown that current text classification models are fragile and sensitive to simple perturbations. In this work, we propose a novel adversarial training approach, LexicalAT, to improve the …...

AbstractAutomatic question generation (QG) is a useful yet challenging task in NLP. Recent neural network-based approaches represent the state-of-the-art in this task. In this work, we attempt to strengthen them …...

AbstractAdvances on deep generative models have attracted significant research interest in neural topic modeling. The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs …...

AbstractKB-to-text task aims at generating texts based on the given KB triples. Traditional methods usually map KB triples to sentences via a supervised seq-to-seq model. However, existing annotated datasets are …...

ELECTRA (Clark et al., 2020a) pretrains a dis- criminator to detect replaced tokens, where the replacements are sampled from a gener- ator trained with masked language modeling. Despite the compelling …...

AbstractRecent studies on neural networks with pre-trained weights (i.e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located. …...

AbstractBootstrapping has become the mainstream method for entity set expansion. Conventional bootstrapping methods mostly define the expansion boundary using seed-based distance metrics, which heavily depend on the quality of selected …...