| Challenge: | Using a variational inference procedure, we factor each training glyph into a combination of a character-specific content embedding and a latent font-specific style variable. |
| Approach: | They propose a deep factorization model that disentangles content from style by factorizing each training glyph into a latent content embedding and a learned embeddable character. |
| Outcome: | The proposed model outperforms a strong nearest neighbors baseline and state-of-the-art discriminative model on reconstructing missing glyphs from an unknown font given only a small number of observations. |
Similar Papers
Scalable Font Reconstruction with Dual Latent Manifolds (2021.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has shown that fonts with a large number of missing glyphs are difficult to model due to the relative sparsity of most fonts. |
| Approach: | They propose a deep generative model that performs typography analysis and font reconstruction by learning disentangled manifolds of both font style and character shape. |
| Outcome: | The proposed model scales up the number of character types we can model compared to previous methods . it can generalize to characters that were not observed during training time, and it compares favorably to other models . |
A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing (2020.acl-main)
Copied to clipboard
| Challenge: | Scholars often need to go beyond textual analysis for establishing provenance of historical documents. |
| Approach: | They propose a deep and interpretable probabilistic generative model to analyze glyph shapes in printed Early Modern documents by generating a latent vector responsible for inking variations, jitter, noise and other unforeseen phenomena. |
| Outcome: | The proposed model outperforms interpretable clustering baselines and overly-flexible deep generative models on the task of completely unsupervised discovery of typefaces in mixed-fonts documents. |
Learning Interpretable Style Embeddings via Prompting LLMs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has treated the style of a text as separable from the content. |
| Approach: | They use prompting to perform stylometry on a large number of texts to generate a synthetic stylometric dataset. |
| Outcome: | The proposed model trains human-interpretable representations on a large stylometric dataset and a linguistic model for style representation learning. |
Disentangled Representation Learning for Non-Parallel Text Style Transfer (P19-1)
Copied to clipboard
| Challenge: | a paper aims to disentangle latent representations of style and content in language models . auxiliary multi-task and adversarial objectives are used to disentangle the latent space . |
| Approach: | They propose a simple yet effective approach to disentangling latent representations . they propose auxiliary multi-task and adversarial objectives to disentangle style and content . |
| Outcome: | The proposed approach achieves high performance in terms of transfer accuracy, content preservation, and language fluency compared to previous approaches . |
Style Vectors for Steering Generative Large Language Models (2024.findings-eacl)
Copied to clipboard
Kai Konen, Sophie Jentzsch, Diaoulé Diallo, Peer Schütt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, Tobias Hecking
| Challenge: | Large language models (LLMs) can be trained on vast corpora and can generate text in a nuanced and parameterisable way. |
| Approach: | They propose to add style vectors to the activations of hidden layers during text generation to steer output towards specific styles. |
| Outcome: | The proposed approach differs from prompt engineering in that it can be nuanced and parameterisable. |
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text style transfer require style-labeled training data, but use only labeled data at inference time. |
| Approach: | They propose a method that uses readily-available unlabeled text to train style transfer . they use a style vector to condition a decoder to perform style transfer using unlabelled text . |
| Outcome: | The proposed method is competitive on sentiment transfer, even compared to models trained fully on labeled data. |
Deep Latent Variable Models of Natural Language (D18-3)
Copied to clipboard
| Challenge: | In this tutorial, we will discuss the challenges of applying neural variational inference to NLP problems. |
| Approach: | The tutorial will cover deep latent variable models in the case where exact inference over the latent variables is tractable. |
| Outcome: | The proposed tutorial will cover deep latent variable models in the case where inference cannot be performed tractably and when it is not . |
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples (2025.naacl-long)
Copied to clipboard
Ajay Patel, Jiacheng Zhu, Justin Qiu, Zachary Horvitz, Marianna Apidianaki, Kathleen McKeown, Chris Callison-Burch
| Challenge: | Existing methods for embedding text are limited by the imperfect nature of data acquired under such assumptions. |
| Approach: | They propose a new approach to training stronger content-independent style embeddings using a synthetic dataset of near-exact paraphrases with controlled style variations. |
| Outcome: | The proposed model outperforms existing methods in real-world benchmarks and outperformed leading style representations in downstream applications. |
Compositional Generalization by Factorizing Alignment and Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | a crucial property underlying the expressive power of human language is its systematicity. |
| Approach: | They propose to make an analogous separation between alignment and translation in neural machine translation to capture compositional structure. |
| Outcome: | The proposed architecture outperforms existing neural networks on a compositional generalization task without supervision. |
Deep Generative Model for Joint Alignment and Word Representation (N18-1)
Copied to clipboard
| Challenge: | EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. |
| Approach: | They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions. |
| Outcome: | The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity. |