Дискриминатор
Related Papers
Adversarial Learning for Neural Dialogue Generation
AbstractWe apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem …...
A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators
AbstractVisual Question Generation (VQG) aims to ask natural questions about an image automatically. Existing research focus on training model to fit the annotated data set that makes it indifferent from …...
Context Encoder for Analogies on Strings
We propose a model based on context en- coder to solve formal analogies on strings like aaabbbccc : aaaabbbbcccc :: abc : x ⇒ x = aabbcc or ubid : …...
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
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. …...
A Compact and Language-Sensitive Multilingual Translation Method
AbstractMultilingual neural machine translation (Multi-NMT) with one encoder-decoder model has made remarkable progress due to its simple deployment. However, this multilingual translation paradigm does not make full use of language …...
Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning
AbstractNeural Machine Translation (NMT) optimized by Maximum Likelihood Estimation (MLE) lacks the guarantee of translation adequacy. To alleviate this problem, we propose an NMT approach that heightens the adequacy in …...
AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER
AbstractNeural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. …...
Learning to Sample Replacements for ELECTRA Pre-Training
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 …...
OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification
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. …...
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
AbstractNeural language models are known to have a high capacity for memorization of training samples. This may have serious privacy im- plications when training models on user content such as …...
Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
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 …...
Progressive Self-Training with Discriminator for Aspect Term Extraction
AbstractAspect term extraction aims to extract aspect terms from a review sentence that users have expressed opinions on. One of the remaining challenges for aspect term extraction resides in the …...
Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis
AbstractAspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards a given aspect term in a sentence on the fine-grained level, which usually requires a good understanding of contextual …...
PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding
AbstractLarge language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy …...
Bridging the Gap between Native Text and Translated Text through Adversarial Learning: A Case Study on Cross-Lingual Event Extraction
AbstractRecent research in cross-lingual learning has found that combining large-scale pretrained multilingual language models with machine translation can yield good performance. We explore this idea for cross-lingual event extraction with …...