BeamR: Beam Reweighing with Attribute Discriminators for Controllable Text Generation (2022.findings-aacl)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have led to the availability of large pre-trained language models with rich generative capabilities. |
| Approach: | They propose a method to combine generative LMs with attribute discriminators to control different attributes of text generation. |
| Outcome: | The proposed method performs better than existing state-of-the-art approaches in sentiment steering and machine translation formality tasks. |
Similar Papers
Incremental Beam Manipulation for Natural Language Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | a larger beam size can lead to deteriorating performance of natural language generation systems due to model errors . performance of NLG systems can plateau or even decrease when beam sizes larger than 10 are used . |
| Approach: | They propose to rerank the output of beam search to produce a good set of hypotheses . they propose incremental beam manipulation to discarded hypothese . |
| Outcome: | The proposed method outperforms a strong reranker on the E2E and WebNLG datasets while being on par with the existing method. |
Attribute Alignment: Controlling Text Generation from Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models can generate text with sentiment polarity or specific topics without changing the original model parameters. |
| Approach: | They propose a method for controlling text generation by aligning disentangled attribute representations. |
| Outcome: | The proposed method shows large performance gains while maintaining diversity and fluency. |
Discriminative Reranking for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | reranking models allow the integration of rich features to select a better output hypothesis within an n-best list or lattice. |
| Approach: | They use discriminative reranking to train a large transformer architecture to train an ranked list of hypotheses. |
| Outcome: | Experiments on four WMT directions show that discriminative reranking improves translation quality. |
First the Worst: Finding Better Gender Translations During Beam Search (2022.findings-acl)
Copied to clipboard
| Challenge: | Neural language generation models optimized by likelihood tend towards 'safe' word choice. |
| Approach: | They propose to use beam search to improve gender diversity in n-best lists and rerank n best lists using gender features obtained from the source sentence to address this problem. |
| Outcome: | The proposed approach improves gender diversity in n-best lists and reranks n best lists using gender features obtained from the source sentence. |
Don’t Add, don’t Miss: Effective Content Preserving Generation from Pre-Selected Text Spans (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing CTR models are mediocre and lack reliable performance . authors propose an explicit decomposition of these two subtasks into a single task . |
| Approach: | They propose an isolated task that challenges models to generate coherent text conforming to pre-selected content within the input text ("highlights") authors propose a high-quality, open-source CTR model that tackles two prior key limitations: inadequate enforcement of the content-preservation constraint, and suboptimal silver training data. |
| Outcome: | The proposed model significantly improves silver training data quality over the existing model, with up to 30 ROUGE-L points. |
On Decoding Strategies for Neural Text Generators (2022.tacl-1)
Copied to clipboard
| Challenge: | a recent study suggests that decoding strategies may be more important than the model architecture itself when generating text from probabilistic models. |
| Approach: | They propose to measure changes in attributes of generated text as a function of decoding strategy and task using human and automatic evaluation. |
| Outcome: | The proposed study shows that decoding strategies do not always transfer across tasks . authors show that the differences in attributes are not always consistent across tasks, they say . |
Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work focuses on generating sentences satisfying pre-specified attributes such as topic and sentiment, yet suffers from increases in storage and inference time. |
| Approach: | They propose a method that uses a pre-trained continuous vector to generate a fixed pre-trainable language model to satisfy a specified attribute. |
| Outcome: | The proposed model can achieve improvements on eleven attribute-specific generation tasks with 0.08% extra training parameters. |
Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for text classification using autoregressive language models are limited . authors propose a novel technique for text classification using autoreregressives . |
| Approach: | They propose a two-step technique for text classification using autoregressive language models . they use a set of perplexity and log-likelihood based numeric features to elicit a text instance . |
| Outcome: | The proposed technique eliminates parameter updates in LMs and does not limit training examples . it is evaluated across 5 datasets and compares with multiple competent baselines . |
Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies on controlled text generation focus on single-attribute control, but in practical applications, they lack controllability. |
| Approach: | They propose a framework for multi-attribute controlled text generation that can effectively generate texts with more attributes. |
| Outcome: | The proposed framework achieves remarkable controllability while keeping the text fluent and diverse. |
Controlling the Focus of Pretrained Language Generation Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing mechanisms to control the model's focus are not available for pretrained transformer-based language generation models. |
| Approach: | They propose to augment a pretrained model with trainable "focus vectors" that are directly applied to the model's embeddings while the model itself is kept fixed. |
| Outcome: | The proposed model is able to generate relevant outputs from user-selected highlights while keeping the model fixed. |