Related papers: Robust (Controlled) Table-to-Text Generation with …

Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the generation. \citet{chen2020logic2text} have addressed this…

Previous work on controllable text generation has explored the idea of control from the latent space, such as optimizing a representation with attribute-related classifiers or sampling a representation from relevant discrete samples.…

Large Language Models (LLMs), already shown to ace various unstructured text comprehension tasks, have also remarkably been shown to tackle table (structured) comprehension tasks without specific training. Building on earlier studies of…

Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learning the correspondence between tables and texts. However,…

Neural data-to-text generation models have achieved significant advancement in recent years. However, these models have two shortcomings: the generated texts tend to miss some vital information, and they often generate descriptions that are…

In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq model to robust…

This paper presents Text2Structure3D, a graph-based Machine Learning (ML) model that generates equilibrium structures from natural language prompts. Text2Structure3D is designed to support new intuitive ways of design exploration and…

We investigate the integration of a planning mechanism into sequence-to-sequence models using attention. We develop a model which can plan ahead in the future when it computes its alignments between input and output sequences, constructing…

Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation. Yet, while current methods are capable of producing a coherent text which is several hundred words long, attaining…

Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we…

The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and "hallucination". Due to the…

Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-of-the-art (SOTA) sequence-based models like the Transformer…

Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts. However, large proportions of generated texts do not actually conform to the input data. To address this…

Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…

The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen…

In Table-to-Text (T2T) generation, existing approaches predominantly focus on providing objective descriptions of tabular data. However, generating text that incorporates subjectivity, where subjectivity refers to interpretations beyond raw…

Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…

Transforming dense, detailed, unstructured text into an interpretable and summarised table, also colloquially known as Text-to-Table generation, is an essential task for information retrieval. Current methods, however, miss out on how and…

Training effective Text-to-SQL models remains challenging due to the scarcity of high-quality, diverse, and structurally complex datasets. Existing methods either rely on limited human-annotated corpora, or synthesize datasets directly by…

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…