Related papers: Controllable and Diverse Text Generation in E-comm…
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying text segments (e.g., words or phrases) from an existing…
Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic text. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient,…
When thinking about dressing oneself, people often have a theme in mind whether they're going to a tropical getaway or wish to appear attractive at a cocktail party. A useful outfit generation system should come up with clothing items that…
The categorization of massive e-Commerce data is a crucial, well-studied task, which is prevalent in industrial settings. In this work, we aim to improve an existing product categorization model that is already in use by a major web…
In recent years, significant advancements have been made in text-driven 3D content generation. However, several challenges remain. In practical applications, users often provide extremely simple text inputs while expecting high-quality 3D…
We consider the task of text generation in language models with constraints specified in natural language. To this end, we first create a challenging benchmark Cognac that provides as input to the model a topic with example text, along with…
Controlled text generation is a very important task in the arena of natural language processing due to its promising applications. In order to achieve this task we mainly introduce the novel soft prompt tuning method of using soft prompts…
Personalized storefronts in large e-commerce marketplaces are often assembled from many independent components: static themes per page section ("placement"), retrieval systems to fetch eligible products per placement, and pointwise rankers…
Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate affective (emotional) text. We posit a model…
As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains…
We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both "pointwise" and "distributional" constraints over…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text. We release CTRL, a 1.63 billion-parameter conditional transformer language model, trained to…
Online advertising is an important revenue source for many IT companies. In the search advertising scenario, advertisement text that meets the need of the search query would be more attractive to the user. However, the manual creation of…
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-trivial, as it often requires a large number of iterations…
Controlled text generation is very important for the practical use of language models because it ensures that the produced text includes only the desired attributes from a specific domain or dataset. Existing methods, however, are…
Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new challenges to the neural…
In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the…
Controllable text generation is a fundamental aspect of natural language generation, with numerous methods proposed for different constraint types. However, these approaches often require significant architectural or decoding modifications,…
This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the…