Related papers: MReD: A Meta-Review Dataset for Structure-Controll…

Is it possible to train a general metric for evaluating text generation quality without human annotated ratings? Existing learned metrics either perform unsatisfactorily across text generation tasks or require human ratings for training on…

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…

As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on…

We consider the problem of automatically generating a narrative biomedical evidence summary from multiple trial reports. We evaluate modern neural models for abstractive summarization of relevant article abstracts from systematic reviews…

Text-to-3D (T23D) generation has emerged as a crucial visual generation task, aiming at synthesizing 3D content from textual descriptions. Studies of this task are currently shifting from per-scene T23D, which requires optimization of the…

Formulating statements that support diverse or controversial stances on specific topics is vital for platforms that enable user expression, reshape political discourse, and drive social critique and information dissemination. With the rise…

Modern models for text generation show state-of-the-art results in many natural language processing tasks. In this work, we explore the effectiveness of abstractive text summarization models for keyphrase selection. A list of keyphrases is…

Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content. Documents such as scientific literature contain rich…

Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs. In this paper, we propose a controllable dialogue generation model to steer response generation…

We present a novel summarization framework for reviews of products and services by selecting informative and concise text segments from the reviews. Our method consists of two major steps. First, we identify five frequently occurring…

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.…

Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be…

Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box architecture. As a result, the content to be described in the text…

We propose a text editor to help users plan, structure and reflect on their writing process. It provides continuously updated paragraph-wise summaries as margin annotations, using automatic text summarization. Summary levels range from full…

We present DART, an open domain structured DAta Record to Text generation dataset with over 82k instances (DARTs). Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of…

Neural text generation has made tremendous progress in various tasks. One common characteristic of most of the tasks is that the texts are not restricted to some rigid formats when generating. However, we may confront some special text…

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

Existing datasets for regular expression (regex) generation from natural language are limited in complexity; compared to regex tasks that users post on StackOverflow, the regexes in these datasets are simple, and the language used to…

Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects by shifting the distribution of generated text towards a desired style, e.g., a set of topics. Subsequently, the…

Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…