Papers with reconstruction loss
Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training (2021.eacl-srw)
Copied to clipboard
| Challenge: | Existing models for generating diverse texts are not pre-trained . generative adversarial networks suffer from mode-collapsing if they are not trained . |
| Approach: | They propose a GAN model that produces diverse texts conditioned by latent code . they propose to use Gumbel-Softmax distribution for word sampling . |
| Outcome: | The proposed model is competitive with existing models, which requires pre-training. |
Unsupervised KB-to-Text Generation with Auxiliary Triple Extraction using Dual Learning (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods to generate text from KB triples are limited and expensive . a novel approach is proposed to train the generation model in unsupervised way . |
| Approach: | They propose a method which trains the generation model in a completely unsupervised way with unaligned raw text data and KB triples. |
| Outcome: | The proposed method outperforms existing methods and is cost-effective. |
GloCOM: A Short Text Neural Topic Model via Global Clustering Context (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing neural topic models often overlook uncovering hidden topics from short texts due to data sparsity, poor aggregation quality, and difficulty in inferring topic proportions for individual documents. |
| Approach: | They propose a model which constructs global clustering contexts for short texts using text embeddings from pre-trained language models. |
| Outcome: | The proposed model outperforms state-of-the-art models on short texts in topic quality and document representation. |
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. |
Hierarchy Response Learning for Neural Conversation Generation (D19-1)
Copied to clipboard
| Challenge: | Neural conversation generation models can't perceive and express the intention effectively, causing dull and generic responses. |
| Approach: | They propose a hierarchical response generation model to capture conversation intention . they propose an expression reconstruction model and an expression attention model . |
| Outcome: | The proposed model can generate the responses with more appropriate content and expression. |
Semi-supervised New Event Type Induction and Description via Contrastive Loss-Enforced Batch Attention (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for event extraction use annotated event types but are expensive and time-consuming. |
| Approach: | They propose a semi-supervised approach to learning new event types using a masked contrastive loss. |
| Outcome: | The proposed method learns similarities between clusters by enforcing an attention mechanism over the data minibatch. |
Do sequence-to-sequence VAEs learn global features of sentences? (2020.emnlp-main)
Copied to clipboard
| Challenge: | Autoregressive language models are often trained without explicit conditioning labels . authors question claim that latent vectors can capture global features in unsupervised manner . |
| Approach: | They propose to use a sequence-to-sequence architecture to learn latent variables . they find that VAEs are prone to memorizing the first words and sentence length . |
| Outcome: | The proposed model is prone to memorizing the first words and sentence length, the authors show . et al., 2016: a new model learns latent variables that are more global, more predictive of topic or topic labels . authors question this claim, say it is a waste of time and money . |