Related papers: R2D2: Robust Data-to-Text with Replacement Detecti…
A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text contains all and only facts supported by the input data. We propose a new metric for…
Methods to generate text from structured data have advanced significantly in recent years, primarily due to fine-tuning of pre-trained language models on large datasets. However, such models can fail to produce output faithful to the input…
End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges in generalizing to new domains and generating semantically consistent text. In this…
Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from…
Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions. Most existing methods ignore the faithfulness between a generated text description and the original table, leading to generated…
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus try to evaluate the generation faithfulness with two…
Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables. There currently exists two challenges in the field: 1) Faithfulness: how to generate sentences that are factually correct given the…
Recent neural approaches to data-to-text generation have mostly focused on improving content fidelity while lacking explicit control over writing styles (e.g., word choices, sentence structures). More traditional systems use templates to…
Data-to-text (D2T) and text-to-data (T2D) are dual tasks that convert structured data, such as graphs or tables into fluent text, and vice versa. These tasks are usually handled separately and use corpora extracted from a single source.…
Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models. This advancement has resulted in more fluent, coherent and even properties…
Existing data-to-text generation efforts mainly focus on generating a coherent text from non-linguistic input data, such as tables and attribute-value pairs, but overlook that different application scenarios may require texts of different…
Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines.…
Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a…
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…
The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods…
Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary…
In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how to avoid finetuning pretrained language models (PLMs) on D2T generation datasets…
For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…
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…
Knowledge base is one of the main forms to represent information in a structured way. A knowledge base typically consists of Resource Description Frameworks (RDF) triples which describe the entities and their relations. Generating natural…