Related papers: Controllable and Diverse Text Generation in E-comm…
Product copywriting is a critical component of e-commerce recommendation platforms. It aims to attract users' interest and improve user experience by highlighting product characteristics with textual descriptions. In this paper, we report…
The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…
Text generation is the automated process of producing written or spoken language using computational methods. It involves generating coherent and contextually relevant text based on predefined rules or learned patterns. However, challenges…
Ad creatives are one of the prominent mediums for online e-commerce advertisements. Ad creatives with enjoyable visual appearance may increase the click-through rate (CTR) of products. Ad creatives are typically handcrafted by advertisers…
Multiple-choice cloze questions are commonly used to assess linguistic proficiency and comprehension. However, generating high-quality distractors remains challenging, as existing methods often lack adaptability and control over difficulty…
Generating a vivid, novel, and diverse essay with only several given topic words is a challenging task of natural language generation. In previous work, there are two problems left unsolved: neglect of sentiment beneath the text and…
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We propose a novel controlled text…
A key distinguishing feature of conversational recommender systems over traditional recommender systems is their ability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to…
Controllable text generation is a growing field within natural language generation (NLG) that focuses on producing text that meets specific constraints in real-world applications. Previous approaches, such as plug-and-play controllers…
Online sellers and advertisers are recommended keyphrases for their listed products, which they bid on to enhance their sales. One popular paradigm that generates such recommendations is Extreme Multi-Label Classification (XMC), which…
Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is…
An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional Image Content Generation (C-EICG), which aims to generate images that remain faithful to a…
Modern online experimentation faces two bottlenecks: scarce traffic forces tough choices on which variants to test, and post-hoc insight extraction is manual, inconsistent, and often content-agnostic. Meanwhile, organizations underuse…
Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel framework that uses large-scale language models and adds…
Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention. Although methods based on parameter efficient tuning like…
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…
Generating stylistic text with specific attributes is a key problem in controllable text generation. Recently, diffusion models have emerged as a powerful paradigm for both visual and textual generation. Existing approaches can be broadly…
Controllable text generation (CTG) aims to generate text with desired attributes, and decoding-time-based methods have shown promising performance on this task. However, in this paper, we identify the phenomenon of Attribute Collapse for…
To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution…
With the rapid evolution of Large Language Models (LLMs), generative recommendation is gradually reshaping the paradigm of recommender systems. However, most existing methods remain confined to the interaction-driven next-item prediction…