相关论文: Towards Controllable and Personalized Review Gener…

Conversational recommender systems aim to provide personalized recommendations via natural language interactions. However, existing approaches either decouple recommendation from dialog generation or rely on retrieval-based pipelines,…

In the paraphrase generation task, source sentences often contain phrases that should not be altered. Which phrases, however, can be context dependent and can vary by application. Our solution to this challenge is to provide the user with…

Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the de facto metrics to evaluate tasks such as image…

This work explores the reproducibility of CFGAN. CFGAN and its family of models (TagRec, MTPR, and CRGAN) learn to generate personalized and fake-but-realistic rankings of preferences for top-N recommendations by using previous…

Automatic news comment generation is a new testbed for techniques of natural language generation. In this paper, we propose a "read-attend-comment" procedure for news comment generation and formalize the procedure with a reading network and…

In the current field of computer vision, automatically generating texts from given images has been a fully worked technique. Up till now, most works of this area focus on image content describing, namely image-captioning. However, rare…

Fine granularity is an essential requirement for controllable text generation, which has seen rapid growth with the ability of LLMs. However, existing methods focus mainly on a small set of attributes like 3 to 5, and their performance…

Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of…

Personalized review response generation presents a significant challenge in domains where user information is limited, such as food delivery platforms. While large language models (LLMs) offer powerful text generation capabilities, they…

We introduce CGA, a conditional VAE architecture, to control, generate, and augment text. CGA is able to generate natural English sentences controlling multiple semantic and syntactic attributes by combining adversarial learning with a…

Human evaluation for natural language generation (NLG) often suffers from inconsistent user ratings. While previous research tends to attribute this problem to individual user preferences, we show that the quality of human judgements can…

A number of automatic evaluation metrics have been proposed for natural language generation systems. The most common approach to automatic evaluation is the use of a reference-based metric that compares the model's output with gold-standard…

Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…

Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natural languages. In…

In this paper, we consider controllability as a means to satisfy dynamic preferences of users, enabling them to control recommendations such that their current preference is met. While deep models have shown improved performance for…

Citation generation aims to generate a citation sentence that refers to a chosen paper in the context of a manuscript. However, a rigid citation generation process is at odds with an author's desire to control specific attributes, such as…

Using reviews to learn user and item representations is important for recommender system. Current review based methods can be divided into two categories: (1) the Convolution Neural Network (CNN) based models that extract n-gram features…

The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure…

We propose to augment rating based recommender systems by providing the user with additional information which might help him in his choice or in the understanding of the recommendation. We consider here as a new task, the generation of…

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider…