相关论文: Revisiting Challenges in Data-to-Text Generation w…

Automated fact-checking benchmarks have largely ignored the challenge of verifying claims against real-world, high-volume structured data, instead focusing on small, curated tables. We introduce a new large-scale, multilingual dataset to…

Neural models for automated fact verification have achieved promising results thanks to the availability of large, human-annotated datasets. However, for each new domain that requires fact verification, creating a dataset by manually…

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our…

Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to…

Retrieval Augmented Generation (RAG) works as a backbone for interacting with an enterprise's own data via Conversational Question Answering (ConvQA). In a RAG system, a retriever fetches passages from a collection in response to a…

Most studies on abstractive summarization report ROUGE scores between system and reference summaries. However, we have a concern about the truthfulness of generated summaries: whether all facts of a generated summary are mentioned in the…

Data-to-text generation involves transforming structured data, often represented as predicate-argument tuples, into coherent textual descriptions. Despite recent advances, systems still struggle when confronted with unseen combinations of…

We introduce FACTS Grounding, an online leaderboard and associated benchmark that evaluates language models' ability to generate text that is factually accurate with respect to given context in the user prompt. In our benchmark, each prompt…

Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been developed for various downstream tasks like generating soccer…

Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the faithfulness of existing systems from a new perspective of…

This work presents a new state of the art in reconstruction of surface realizations from obfuscated text. We identify the lack of sufficient training data as the major obstacle to training high-performing models, and solve this issue by…

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…

Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document…

Despite recent success, large neural models often generate factually incorrect text. Compounding this is the lack of a standard automatic evaluation for factuality--it cannot be meaningfully improved if it cannot be measured. Grounded…

Video captioning aims to describe events in a video with natural language. In recent years, many works have focused on improving captioning models' performance. However, like other text generation tasks, it risks introducing factual errors…

Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text,…

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the…

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…

We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description.…

With the widespread consumption of AI-generated content, there has been an increased focus on developing automated tools to verify the factual accuracy of such content. However, prior research and tools developed for fact verification treat…