Related papers: FAST: Improving Controllability for Text Generatio…
Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgments, whereas…
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that…
This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given…
Recent advancements in large language models have revolutionized text generation with their remarkable capabilities. These models can produce controlled texts that closely adhere to specific requirements when prompted appropriately.…
Despite the fact that image captioning models have been able to generate impressive descriptions for a given image, challenges remain: (1) the controllability and diversity of existing models are still far from satisfactory; (2) models…
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control…
Self-training (ST) has prospered again in language understanding by augmenting the fine-tuning of pre-trained language models when labeled data is insufficient. However, it remains challenging to incorporate ST into attribute-controllable…
Much research in recent years has focused on automatic article commenting. However, few of previous studies focus on the controllable generation of comments. Besides, they tend to generate dull and commonplace comments, which further limits…
Question Generation (QG) is a task within Natural Language Processing (NLP) that involves automatically generating questions given an input, typically composed of a text and a target answer. Recent work on QG aims to control the type of…
Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…
Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles generation quality and diversity, textual diffusion suffers…
This paper presents an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. In the context of language model-based audio generation, the…
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…
Multi-aspect controllable text generation aims to control the generated texts in attributes from multiple aspects (e.g., "positive" from sentiment and "sport" from topic). For ease of obtaining training samples, existing works neglect…
One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant…
This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation…
With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for…
Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in…