Генеративті қарсылас желі

AbstractThis paper presents a Generative Adversarial Network (GAN) to model single-turn short-text conversations, which trains a sequence-to-sequence (Seq2Seq) network for response generation simultaneously with a discriminative classifier that measures the …...

AbstractRelation Classification aims to classify the semantic relationship between two marked entities in a given sentence. It plays a vital role in a variety of natural language processing applications. Most …...

AbstractGenerative Adversarial Network (GAN) has been proposed to tackle the exposure bias problem of Neural Machine Translation (NMT). However, the discriminator typically results in the instability of the GAN training …...

AbstractQuestion answering (QA) and question generation (QG) are closely related tasks that could improve each other; however, the connection of these two tasks is not well explored in literature. In …...

AbstractWhile the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity. To tackle this problem, we propose a novel semi-supervised approach …...

AbstractWe present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers …...

AbstractDistant supervision has been widely used in relation extraction tasks without hand-labeled datasets recently. However, the automatically constructed datasets comprise numbers of wrongly labeled negative instances due to the incompleteness …...

AbstractThe objective of non-parallel text style transfer, or controllable text generation, is to alter specific attributes (e.g. sentiment, mood, tense, politeness, etc) of a given text while preserving its remaining …...

AbstractWe propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We …...

AbstractThe challenge of both achieving task completion by querying the knowledge base and generating human-like responses for task-oriented dialogue systems is attracting increasing research attention. In this paper, we propose …...

AbstractRecent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformer based sequence-to-sequence models, as well as variational autoencoder (VAE) and generative adversarial …...

AbstractWe propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed-attention mechanism, and employ …...

AbstractAutomatic transfer of text between domains has become popular in recent times. One of its aims is to preserve the semantic content while adapting to the target domain. However, it …...

AbstractTraining Neural Machine Translation (NMT) models suffers from sparse parallel data, in the infrequent translation scenarios towards low-resource source languages. The existing solutions primarily concentrate on the utilization of Parent-Child …...