Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, object) is predicted as (object, relation, subject)). To address this limitation, we introduce TSET (Triplet Structure Enhanced T5), a model with a novel pretraining stage positioned between the initial T5 pretraining and the fine-tuning for the Text-to-SPARQL task. In this intermediary stage, we introduce a new objective called Triplet Structure Correction (TSC) to train the model on a SPARQL corpus derived from Wikidata. This objective aims to deepen the model’s understanding of the order of triplets. After this specialized pretraining, the model undergoes fine-tuning for SPARQL query generation, augmenting its query-generation capabilities. We also propose a method named “semantic transformation” to fortify the model’s grasp of SPARQL syntax and semantics without compromising the pre-trained weights of T5. Experimental results demonstrate that our proposed TSET outperforms existing methods on three well-established KBQA datasets: LC-QuAD 2.0, QALD-9 plus, and QALD-10, establishing a new state-of-the-art performance (95.0% F1 and 93.1% QM on LC-QuAD 2.0, 75.85% F1 and 61.76% QM on QALD-9 plus, 51.37% F1 and 40.05% QM on QALD-10).
With the advent of big data science, the field of geoscience has undergone a paradigm shift toward data-driven scientific discovery. However, the abundance of geoscience data distributed across multiple sources poses significant challenges to researchers in terms of data compilation, which includes data collection, collation, and database construction. To streamline the data compilation process, we present GeoKnowledgeFusion, a publicly accessible platform for the fusion of text, visual, and tabular knowledge extracted from the geoscience literature. GeoKnowledgeFusion leverages a powerful network of models that provide a joint multimodal understanding of text, image, and tabular data, enabling researchers to efficiently curate and continuously update their databases. To demonstrate the practical applications of GeoKnowledgeFusion, we present two scenarios: the compilation of Sm-Nd isotope data for constructing a domain-specific database and geographic analysis, and the data extraction process for debris flow disasters. The data compilation process for these use cases encompasses various tasks, including PDF pre-processing, target element recognition, human-in-the-loop annotation, and joint multimodal knowledge understanding. The findings consistently reveal patterns that align with manually compiled data, thus affirming the credibility and dependability of our automated data processing tool. To date, GeoKnowledgeFusion has supported forty geoscience research teams within the program by processing over 40,000 documents uploaded by geoscientists.
The rare earth elements Sm and Nd significantly address fundamental questions about crustal growth, such as its spatiotemporal evolution and the interplay between orogenesis and crustal accretion. Their relative immobility during high-grade metamorphism makes the Sm-Nd isotopic system crucial for inferring crustal formation times. Historically, data have been disseminated sporadically in the scientific literature due to complicated and costly sampling procedures, resulting in a fragmented knowledge base. However, the scattering of critical geoscience data across multiple publications poses significant challenges regarding human capital and time. In response, we present an automated tabular extraction method for harvesting tabular geoscience data. We collect 10,624 Sm-Nd data entries from 9,138 tables in over 20,000 geoscience publications using this method. We manually selected 2,118 data points from it to supplement the previously constructed global Sm-Nd dataset, increasing its sample count by over 20%. Our automatic data collection methodology enhances the efficiency of data acquisition processes spanning various scientific domains.
18 July 2024 in IEEE Transactions on Audio, Speech and Language Processing
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially in real-world applications with limited resources. To mitigate the limitation of insufficient labeled data, we propose a novel framework: Adapt-Knowledge-to-Generate (AKG). The core insight of AKG is to adapt unlabeled domain-specific knowledge into the model, which brings at least three benefits: (1) it injects representation of normal table-related descriptions to bridge the topological gap between tabular data and texts; (2) it enables us to use large amounts of unlabeled domain-specific knowledge fully, which can alleviate the PLMs' inherent shortcomings of lacking domain knowledge; (3) it allows us to design various tasks to employ the domain-specific knowledge. Extensive experiments and analyses are conducted on three open-domain, few-shot natural language generation (NLG) data sets: Humans, Songs, and Books. Compared to previous state-of-the-art approaches, our model achieves superior performance in terms of both fluency and accuracy as judged by human and automatic evaluations.
The field of geoscience has experienced a transformative shift towards data-driven scientific discovery in the era of big data science. However, the diverse and variable nature of images obtained from scientific literature presents significant challenges for researchers in terms of data collection. To address this issue, we introduce GeoImageCut, a publicly available toolkit designed to process and extract multiple objects from individual images sourced from geoscience literature. Developed as an essential component of the Deep-Time Digital Earth (DDE) program, GeoImageCut has provided invaluable support to forty geoscience research teams within the program, successfully processing over 10,000 documents. A demonstration of GeoImageCut is available through our Web User Interface (UI) at: https://deepshovel.acemap.cn