Papers with variational autoencoder
Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for learning disentangled representations of real-world data focus on attribute labels or unsupervised methods that manipulate factorization in the latent space of models such as the variational autoencoder (VAE). |
| Approach: | They propose an approach that disentangles select attributes in the latent space based on proximity measures reflecting the similarity between data points with respect to these attributes. |
| Outcome: | The proposed method outperforms the VAE baseline and is competitive with state-of-the-art approaches while being more a general framework applicable to other attribute disentanglement tasks. |
MELOV: Multimodal Entity Linking with Optimized Visual Features in Latent Space (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multimodal entity linking focus on textual contexts but lack in social media vision modality. |
| Approach: | They propose a latent space vision feature optimization framework MELOV to address these challenges . they exploit variational autoencoder to mine shared information and generate text-based visual features . |
| Outcome: | The proposed framework is superior to existing methods on three benchmark datasets. |
Vector Space Interpolation for Query Expansion (2022.aacl-short)
Copied to clipboard
| Challenge: | Topic-sensitive query set expansion is crucial for queries related to sensitive and emerging topics. |
| Approach: | They propose a method for topic-sensitive query set expansion using vector space interpolation. |
| Outcome: | The proposed method generates new queries about the sensitive topic by incorporating set diversity, which is not captured by traditional sentence-level augmentation methods such as paraphrasing or back-translation. |
Semi-supervised New Event Type Induction and Event Detection (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing event extraction studies assume a set of event types and corresponding annotations are given, which could be expensive. |
| Approach: | They propose a semi-supervised task of event type induction to learn seen and unseen types . they use seen type annotations to optimize the process and enforce the reconstruction . |
| Outcome: | The proposed method achieves state-of-the-art on supervised event detection and discovers high-quality new types. |
Neural Attention-Aware Hierarchical Topic Model (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural topic models (NTMs) use deep neural networks to learn topic information. |
| Approach: | They propose a variational autoencoder model that reconstructs sentence and document word counts using bag-of-words embeddings and pre-trained semantic embedders. |
| Outcome: | The proposed model lowers reconstruction errors at sentence and document levels and finds more coherent topics from real-world datasets. |
Diversity-Aware Coherence Loss for Improving Neural Topic Models (2023.acl-short)
Copied to clipboard
| Challenge: | Experimental results show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters. |
| Approach: | They propose a variational autoencoder framework that minimizes the posterior and prior divergence and a diversity-aware coherence loss that encourages the model to learn corpus-level coherency scores while maintaining high diversity between topics. |
| Outcome: | The proposed approach significantly improves the performance of neural topic models without pretraining or additional parameters. |
Unsupervised Relation Extraction: A Variational Autoencoder Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use latent variables and supervised training which requires large datasets. |
| Approach: | They propose a VAE-based unsupervised relation extraction technique that uses latent variables as an intermediate variable instead of a latent variable. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the NYT dataset and outperformed existing methods. |
CaM-Gen: Causally Aware Metric-Guided Text Generation (2022.findings-acl)
Copied to clipboard
| Challenge: | Content is created for a well-defined purpose, often described by a metric or signal . external metrics and content tend to have inherent relationships and not all of them may be of consequence. |
| Approach: | They propose a mechanism to guide generative models by user-defined target metrics . authors propose generative networks guided by causally significant aspects of text . |
| Outcome: | The proposed models beat baselines in terms of the target metric control while maintaining fluency and language quality of the generated text. |
Doc2hash: Learning Discrete Latent variables for Documents Retrieval (N19-1)
Copied to clipboard
| Challenge: | Learning to hash via generative model is a powerful paradigm for fast similarity search in documents retrieval. |
| Approach: | They propose a method that trains a generative model to generate hash codes by using continuous relaxation on priors. |
| Outcome: | The proposed method outperforms other state-of-the-art methods in qualitative and quantitative experiments. |
Unsupervised Few-Bits Semantic Hashing with Implicit Topics Modeling (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for few-bits hashing cannot be guaranteed due to severe information loss. |
| Approach: | They propose a simple unsupervised neural generative semantic hashing method with a focus on few-bits hash. |
| Outcome: | The proposed method improves on the state-of-the-art methods in few-bits hashing. |
Reinforcement Learning for Topic Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Topic modeling is a method to extract information from documents by grouping topics into topics and linking them with words describing them. |
| Approach: | They propose to replace the variational autoencoder with a continuous action space reinforcement learning policy and modify the neural network architecture to weight the ELBO loss. |
| Outcome: | The proposed model outperforms all other unsupervised models and performs on par with or better than most models using supervised labeling and contrastive learning. |
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects. |
| Approach: | They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies. |
| Outcome: | The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed. |
Neural Topic Model with Reinforcement Learning (D19-1)
Copied to clipboard
| Challenge: | Experimental results show superior performance on perplexity and topic coherence measures compared to state-of-the-art topic models. |
| Approach: | They propose to incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model. |
| Outcome: | The proposed model is able to separating background words dynamically from topic words eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models. |
Continuous Language Generative Flow (2021.acl-long)
Copied to clipboard
| Challenge: | Recent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformers. |
| Approach: | They propose a flow-based language generation model that adapts flow-derived generative models to language generation via continuous input embeddings, adapted affine coupling structures, and a novel architecture for autoregressive text generation. |
| Outcome: | The proposed model improves on QG and NMT and improves performance over baselines on SQuAD and TVQA and NML16. |
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in disentanglement work on coarse levels in the disenanglement of closely related properties, such as syntax and semantics in human languages. |
| Approach: | They propose a deep decomposable model based on VAE to disentangle syntax and semantics by using total correlation penalties on KL divergences. |
| Outcome: | The proposed model significantly improves the disentanglement quality between syntactic and semantic representations for semantic similarity tasks and syntaktic similarity task. |
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs. |
| Approach: | They propose to use the variational autoencoder (VAE) for probabilistic sentence generation . they propose a variant of WAE that encourages the stochasticity of the encoder . |
| Outcome: | The proposed variant encourages the stochasticity of the encoder while achieving higher BLEU scores. |
UniMath: A Foundational and Multimodal Mathematical Reasoner (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for interpreting and processing diverse mathematical modalities are limited . existing systems are limited in interpreting complex mathematical tasks and implementing them in a multimodal manner. |
| Approach: | They propose a multimodal mathematical reasoning system that utilizes a fine-tuned T5 model augmented with a variational autoencoder (VAE)-based image tokenizer. |
| Outcome: | The proposed model achieves state-of-the-art performance on SVAMP, GeoQA, and TableMWP datasets and is generalized on two additional datasets. |
Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction (2024.findings-emnlp)
Copied to clipboard
Yuncheng Hua, Yujin Huang, Shuo Huang, Tao Feng, Lizhen Qu, Christopher Bain, Richard Bassed, Reza Haf
| Challenge: | Emotion-cause pair extraction is a task that aims to extract emotions and the events causing such emotions. |
| Approach: | They propose a deep latent model which captures the underlying latent structures of data and utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains. |
| Outcome: | The proposed model outperforms the strongest baseline by approximately 11.05% on a Chinese benchmark and 2.45% on an English benchmark in terms of weighted-average F1 score. |
Better Exploiting Latent Variables in Text Modeling (P19-1)
Copied to clipboard
| Challenge: | Consistent gains in performance on two datasets, Penn Treebank and Yahoo, indicate the generalizability of our method. |
| Approach: | They propose a method to exploit latent variables through hidden state averaging by sampling latent variable multiple times at a gradient step. |
| Outcome: | The proposed method shows consistent gains on two datasets showing that it is generalizable. |
Variational Pretraining for Semi-supervised Text Classification (P19-1)
Copied to clipboard
| Challenge: | Empirically, we show the relative strength of VAMPIRE against computationally expensive contextual embeddings and other popular semi-supervised baselines under low resource settings. |
| Approach: | They propose a lightweight framework for effective text classification when data and computing resources are limited. |
| Outcome: | The proposed framework is compared with expensive contextual embeddings and semi-supervised baselines under low resource settings. |
Neural Topic Modeling based on Cycle Adversarial Training and Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural topic models have been widely used to extract common topics across documents. |
| Approach: | They propose a framework to apply contrastive learning directly to the decoder . they propose 'self-supervised' contrastive loss to make the generator capture similar topic information . |
| Outcome: | The proposed framework outperforms baselines on four benchmark datasets. |
Neural Topic Modeling via Contextual and Graph Information Fusion (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing topic models generate uninformative and incoherent topics that hinder interpretable insights from managing textual data. |
| Approach: | They propose to incorporate contextual and graph information to improve the variational autoencoder framework by combining contextual and bag-of-words information. |
| Outcome: | The proposed framework generates more coherent and diverse topics on three benchmark datasets and achieves strong performance on automatic and manual evaluations. |
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for task-specific natural language generation do not contain any labeled examples. |
| Approach: | They propose a variational autoencoder with disentanglement priors for task-specific natural language generation with none or a handful of task-related labeled examples. |
| Outcome: | The proposed model outperforms baseline models in terms of data augmentation and text style transfer in the few-shot setting. |
Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing topic models often lack sufficient word co-occurrence in short texts, resulting in incoherent topics. |
| Approach: | They propose to use large language models to extend short texts into more detailed sequences before applying topic modeling to solve semantic inconsistency problem. |
| Outcome: | The proposed approach significantly outperforms current state-of-the-art topic models on real-world datasets with extreme data sparsity. |
DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. |
| Approach: | They propose a controllable data synthesis framework based on variational autoencoder which leverages diffusion models to reserve more information of original distribution and format structure in the learned latent distribution. |
| Outcome: | The proposed framework generates high-quality data with performance exceeding that of real data by 2%–7% on seven real-world datasets. |
Opinions Are Not Always Positive: Debiasing Opinion Summarization with Model-Specific and Model-Agnostic Methods (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing opinion summarization frameworks are reluctant to generate negative summaries given input of negative opinions. |
| Approach: | They propose to disentangle input into sentiment-relevant and sentiment-irrelevant components through adversarial loss. |
| Outcome: | The proposed approaches reduce sentiment bias in the existing opinion summarization dataset . the proposed approaches generate better summaries with a more balanced emotional polarity distribution . |
Capturing Latent Modal Association For Multimodal Entity Alignment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for multimodal entity alignment overlook the quality of input modality embeddings during modality interaction, amplifying noise propagation while suppressing discriminative feature representations. |
| Approach: | They propose a model for capturing latent modal association for multimodal entity alignment using a self-attention mechanism to enhance salient information while attenuating noise within individual modality embeddings. |
| Outcome: | The proposed model achieves an absolute 3.1% higher Hits@1 score than the sota method. |