Keyphrase generation (KG) is an essential problem in many natural language processing (NLP) tasks. Deep learning keyphrase generation methods often combine the copy and generating action-aware probabilities to model keyphrase accuracy, ignoring the copy and generating specificities for each keyword. In this work, we design a novel KG method that utilizes reinforcement learning (RL), namely KGAgent, where a relative reward based RL agent makes effective controllable manipulations on the decoupled action-aware policies to further improve the keyphrase generability. While RL is unstable and hard to train, several strategies, including momentum mechanism, distribution alignment and proximal policy optimization, are employed to stabilize the actor-critic network. Additionally, the proposed method reflects algorithm scalability that it can be plugged into any existing deep learning methods under different training paradigms, and consistently achieves higher accuracy than the state-of-the-art methods on the scientific article and social media datasets.

Keyphrase generation is one of the most fundamental tasks in natural language processing (NLP). Most existing works on keyphrase generation mainly focus on using holistic distribution to optimize the negative log-likelihood loss, but they do not directly manipulate the copy and generating spaces, which may reduce the generability of the decoder. Additionally, existing keyphrase models are either unable to determine the dynamic numbers of keyphrases or produce the number of keyphrases implicitly. In this article, we propose a probabilistic keyphrase generation model from copy and generating spaces. The proposed model is built upon the vanilla variational encoder-decoder (VED) framework. On top of VED, two separate latent variables are adopted to model the distribution of data within the latent copy and generating spaces, respectively. Specifically, we adopt a von Mises-Fisher (vMF) distribution to obtain a condensed variable for modifying the generating probability distribution over the predefined vocabulary. Meanwhile, we utilize a clustering module, which is designed to promote Gaussian Mixture learning and subsequently extract a latent variable for the copy probability distribution. Moreover, we utilize a natural property of the Gaussian mixture network and use the number of filtered components to determine the number of keyphrases. The approach is trained based on latent variable probabilistic modeling, neural variational inference, and self-supervised learning. Experiments on social media and scientific article datasets outperform the state-of-the-art baselines in generating accurate predictions and controllable keyphrase numbers.

The onion service is the most important mechanism of the Tor network which enables service providers to publish anonymously various TCP services, such as web services. To access the target onion services, clients first know the 56-byte onion addresses. However, randomly generated onion addresses are difficult to memorize and can be easily used by attackers to generate phishing sites with similar onion addresses. In this paper, we propose a correlated onion address generation approach which is capable of generating a unique onion address via a customized string and a root onion address. This approach enables the generated onion addresses to be computed by clients using a human-memorable string, resulting in easier access to onion services. Based on this approach, we design and implement a Tor Domain Name System (TorDNS) that allows different service providers to register anonymously and clients to access anonymous services quickly through human-memorable pseudo-onion addresses. TorDNS is compatible with existing onion service mechanism and does not introduce additional privacy and security issues. In addition, similarity detection of pseudo-onion addresses can effectively reduce the risk of phishing sites on the Tor network.

Keyphrase generation (KG) aims at condensing the content from the source text to the target concise phrases. Though many KG algorithms have been proposed, most of them are tailored into deep learning settings with various specially designed strategies and may fail in solving the bias exposure problem. Reinforcement Learning (RL), a class of control optimization techniques, are well suited to compensate for some of the limitations of deep learning methods. Nevertheless, RL methods typically suffer from four core difficulties in keyphrase generation: environment interaction and effective exploration, complex action control, reward design, and task-specific obstacle. To tackle this difficult but significant task, we present RegRL-KG, including actor-critic based-reinforcement learning control and L1 policy regularization under the first principle of minimizing the maximum likelihood estimation (MLE) criterion by a sequence-to-sequence (Seq2Seq) deep learnining model, for efficient keyphrase generation. The agent utilizes an actor-critic network to control the generated probability distribution and employs L1 policy regularization to solve the bias exposure problem. Extensive experiments show that our method brings improvement in terms of the evaluation metrics on five scientific article benchmark datasets.

Keyphrase generation aims to generate a set of condensed phrases given a source document.Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from the bias on the source-prediction pair and the bias on the prediction-target pair.To tackle the above biases, we propose a novel correction model CorrKG on top of the MLE pipeline, where the biases are corrected via the optimal transport (OT) and a frequency-based filtering-and-sorting (FreqFS) strategy.Specifically, OT is introduced as the soft correction to facilitate the alignment of salient information and rectify the semantic bias on the source document and predicted keyphrases pair.An adaptive semantic mass learning scheme is conducted on the vanilla OT to achieve a proper pair-wise optimal transport procedure, which promotes the OT calculation brought by rectifying semantic masses dynamically.Besides, the FreqFS strategy is designed as the hard correction to reduce the bias of predicted and target keyphrases, and thus generate accurate and sufficient keyphrases.Extensive experiments over multiple benchmark datasets show that our model achieves superior keyphrase generation as compared with the state-of-the-arts.