ATM:Adversarial-neural Topic Model
Topic models are widely used for thematic structure discovery in text. But traditional topic models often require dedicated inference procedures for specific tasks at hand. Also, they are not designed to generate word-level semantic representations. To address these limitations, we propose a topic modeling approach based on Generative Adversarial Nets (GANs), called Adversarial-neural Topic Model (ATM). The proposed ATM models topics with Dirichlet prior and employs a generator network to capture the semantic patterns among latent topics. Meanwhile, the generator could also produce word-level semantic representations. To illustrate the feasibility of porting ATM to tasks other than topic modeling, we apply ATM for open domain event extraction. Our experimental results on the two public corpora show that ATM generates more coherence topics, outperforming a number of competitive baselines. Moreover, ATM is able to extract meaningful events from news articles.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesEvent ExtractionmodelTopic ModelsSimilar Papers 제목 키워드 기반
Neural Topic Modeling with Cycle-Consistent Adversarial Training
Advances 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…
text-classificationText ClassificationNeural Topic Modeling with Bidirectional Adversarial Training
Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topi…
ClusteringText ClusteringTopic ModelsAdversarial Topic-aware Prompt-tuning for Cross-topic Automated Essay Scoring
Cross-topic automated essay scoring (AES) aims to develop a transferable model capable of effectively evaluating essays on a target topic. A significant challenge in this domain arises from the inherent discrepancies bet…
Automated Essay ScoringTopic-oriented Adversarial Attacks against Black-box Neural Ranking Models
Neural ranking models (NRMs) have attracted considerable attention in information retrieval. Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks, which might be leveraged by black-h…
Information RetrievalRetrievalA Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews
The flexibility of the inference process in Variational Autoencoders (VAEs) has recently led to revising traditional probabilistic topic models giving rise to Neural Topic Models (NTMs). Although these approaches have ac…
DisentanglementSentiment AnalysisSentiment ClassificationTopic Models