Existing pre-trained models for knowledgegraph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments. To tackle these problems, we propose a graph-text joint representation learning model called JointGT. During encoding, we devise a structure-aware semantic aggregation module which is plugged into each Transformer layer to preserve the graph structure. Furthermore, we propose three new pre-training tasks to explicitly enhance the graph-text alignment including respective text / graph reconstruction, and graph-text alignment in the embedding space via Optimal Transport. Experiments show that JointGT obtains new stateof-the-art performance on various KG-to-text datasets 1 .
The rapid and accurate identification of sunflower lodging is important for the assessment of damage to sunflower crops. To develop a fast and accurate method of extraction of information on sunflower lodging, this study improves the inputs to SegNet and U-Net to render them suitable for multi-band image processing. Random forest and two improved deep learning methods are combined with RGB, RGB + NIR, RGB + red-edge, and RGB + NIR + red-edge bands of multi-spectral images captured by a UAV (unmanned aerial vehicle) to construct 12 models to extract information on sunflower lodging. These models are then combined with the method used to ignore edge-related information to predict sunflower lodging. The results of experiments show that the deep learning methods were superior to the random forest method in terms of the obtained lodging information and accuracy. The predictive accuracy of the model constructed by using a combination of SegNet and RGB + NIR had the highest overall accuracy of 88.23%. Adding NIR to RGB improved the accuracy of extraction of the lodging information whereas adding red-edge reduced it. An overlay analysis of the results for the lodging area shows that the extraction error was mainly caused by the failure of the model to recognize lodging in mixed areas and low-coverage areas. The predictive accuracy of information on sunflower lodging when edge-related information was ignored was about 2% higher than that obtained by using the direct splicing method.
In this study, a game-based production experiment was adopted to examine the prosodic realization of syntactically ambiguous sentences by Chinese learners of English as a foreign language (EFL hereafter). 20 Chinese undergraduates and 10 native speakers of American English participated in this experiment. Subjects followed the guides in pictures and instructed listeners to move objects on the computer screen by using the critical instructions with prepositional attachment sentences (PP-attachment hereafter). In all, 10 pairs of ambiguous PP-attachment sentences that might refer to one situation or another were adopted. It was found that both the native speakers and Chinese EFL learners used pre-boundary lengthening and pause to distinguish the alternative meanings of the ambiguous PP-attachment sentences. While native speakers also showed domain-initial strengthening which may be related to the length of previous phrase, and greater preboundary lengthening and longer pause than the learners. In addition, native speakers displayed pitch reset at the prosodic boundary, indicating a pitch declination of the utterances. However, the learners might not consistently use pitch reset at the prosodic boundary.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.