Related papers: Learning Better Representation for Tables by Self-…

In recent years, representation learning has become the research focus of the machine learning community. Large-scale neural networks are a crucial step toward achieving general intelligence, with their success largely attributed to their…

Text generation is a fundamental building block in natural language processing tasks. Existing sequential models performs autoregression directly over the text sequence and have difficulty generating long sentences of complex structures.…

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using the input concept dataset and novel textual prompt. However,…

In recent visual self-supervision works, an imitated classification objective, called pretext task, is established by assigning labels to transformed or augmented input images. The goal of pretext can be predicting what transformations are…

Table-to-text systems generate natural language statements from structured data like tables. While end-to-end techniques suffer from low factual correctness (fidelity), a previous study reported gains when using manual logical forms (LF)…

Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these…

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural…

Information distribution by electronic messages is a privileged means of transmission for many businesses and individuals, often under the form of plain-text tables. As their number grows, it becomes necessary to use an algorithm to extract…

In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Table-to-text generation aims to generate a description for a factual table which can be viewed as a set of field-value records. To encode both the content and the structure of a table, we propose a novel structure-aware seq2seq…

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of…

Tables in Web documents are pervasive and can be directly used to answer many of the queries searched on the Web, motivating their integration in question answering. Very often information presented in tables is succinct and hard to…

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…

Distilling large, unstructured text into a structured, condensed form such as tables is an open research problem. One of the primary challenges in automatically generating tables is ensuring their syntactic validity. Prior approaches…

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

Understanding whether a generated table is of good quality is important to be able to use it in creating or editing documents using automatic methods. In this work, we underline that existing measures for table quality evaluation fail to…

Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks…