Search

Generating diverse and factual text is challenging and is receiving increasing attention. By sampling from the latent space, variational autoencoder-based models have recently enhanced the diversity of generated text. However, existing research predominantly depends on summarization models to offer paragraph-level semantic information for enhancing factual correctness. The challenge lies in effectively generating factual text using sentence-level variational autoencoder-based models. In this paper, a novel model called fact-aware conditional variational autoencoder is proposed to balance the factual correctness and diversity of generated text. Specifically, our model encodes the input sentences and uses them as facts to build a conditional variational autoencoder network. By training a conditional variational autoencoder network, the model is enabled to generate text based on input facts. Building upon this foundation, the input text is passed to the discriminator along with the generated text. By employing adversarial training, the model is encouraged to generate text that is indistinguishable to the discriminator, thereby enhancing the quality of the generated text. To further improve the factual correctness, inspired by the natural language inference system, the entailment recognition task is introduced to be trained together with the discriminator via multi-task learning. Moreover, based on the entailment recognition results, a penalty term is further proposed to reconstruct the loss of our model, forcing the generator to generate text consistent with the facts. Experimental results demonstrate that compared with competitive models, our model has achieved substantial improvements in both the quality and factual correctness of the text, despite only sacrificing a small amount of diversity. Furthermore, when considering a comprehensive evaluation of diversity and quality metrics, our model has also demonstrated the best performance. [ABSTRACT FROM AUTHOR]

SUMMARY: The characterization of cis‐regulatory DNA elements (CREs) is essential for deciphering the regulation of gene expression in eukaryotes. Although there have been endeavors to identify CREs in plants, the properties of CREs in polyploid genomes are still largely unknown. Here, we conducted the genome‐wide identification of DNase I‐hypersensitive sites (DHSs) in leaf and stem tissues of the auto‐octoploid species Saccharum officinarum. We revealed that DHSs showed highly similar distributions in the genomes of these two S. officinarum tissues. Notably, we observed that approximately 74% of DHSs were located in distal intergenic regions, suggesting considerable differences in the abundance of distal CREs between S. officinarum and other plants. Leaf‐ and stem‐dependent transcriptional regulatory networks were also developed by mining the binding motifs of transcription factors (TFs) from tissue‐specific DHSs. Four TEOSINTE BRANCHED 1, CYCLOIDEA, and PCF1 (TCP) TFs (TCP2, TCP4, TCP7, and TCP14) and two ethylene‐responsive factors (ERFs) (ERF109 and ERF03) showed strong causal connections with short binding distances from each other, pointing to their possible roles in the regulatory networks of leaf and stem development. Through functional validation in transiently transgenic protoplasts, we isolate a set of tissue‐specific promoters. Overall, the DHS maps presented here offer a global view of the potential transcriptional regulatory elements in polyploid sugarcane and can be expected to serve as a valuable resource for both transcriptional network elucidation and genome editing in sugarcane breeding. Significance Statement: Whole genome‐wide open chromatin maps were constructed in the auto‐octoploid species Saccharum officinarum. We revealed that distal open chromatin was prevalent in sugarcane. Leaf‐ and stem‐specific promoters were isolated, which can be expected to serve as a valuable resource for both transcriptional network elucidation and genome editing in sugarcane breeding. [ABSTRACT FROM AUTHOR]