Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this paper, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. Statement Position Code (SPC) is defined to transform a nested SQL query into a set of non-nested SELECT statements; a sketch-based slot filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved competitive result of 58.2% accuracy on the challenging Spider benchmark. At the time of paper submission (April 2020), RYANSQL v2, a variant of original RYANSQL, is positioned at 3rd place among all systems and 1st place among the systems not using database content with 60.6% exact matching accuracy. The source code is available at https://github.com/kakaoenterprise/RYANSQL.

Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this paper, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex Text-to-SQL tasks for cross-domain databases. Statement Position Code (SPC) is defined to transform a nested SQL query into a set of nonnested SELECT statements; a sketch-based slot filling approach is proposed to synthesize each SELECT statement for its corresponding SPC. Additionally, two input manipulation methods are presented to improve generation performance further. RYANSQL achieved 58.2% accuracy on the challenging Spider benchmark, which is a 3.2%p improvement over previous state-of-the-art approaches. At the time of writing, RYANSQL achieves the first position on the Spider leaderboard.

Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Many existing works for text summarization are generally evaluated by using recall-oriented understudy for gisting evaluation (ROUGE) scores. However, as ROUGE scores are computed based on n-gram overlap, they do not reflect semantic meaning correspondences between generated and reference summaries. Because Korean is an agglutinative language that combines various morphemes into a word that express several meanings, ROUGE is not suitable for Korean summarization. In this paper, we propose evaluation metrics that reflect semantic meanings of a reference summary and the original document, Reference and Document Aware Semantic Score (RDASS). We then propose a method for improving the correlation of the metrics with human judgment. Evaluation results show that the correlation with human judgment is significantly higher for our evaluation metrics than for ROUGE scores.

Schottky diode-based temperature sensors are the most common commercially available temperature sensors, and they are attracting increasing interest owing to their higher Schottky barrier height compared to their silicon counterparts. Therefore, this paper presents a comparison of the thermal sensitivity variation trend in temperature sensors, based on dual 4H-SiC junction barrier Schottky (JBS) diodes and Schottky barrier diodes (SBDs). The forward bias current–voltage characteristics were acquired by sweeping the DC bias voltage from 0 to 3 V. The dual JBS sensor exhibited a higher peak sensitivity (4.32 mV/K) than the sensitivity exhibited by the SBD sensor (2.85 mV/K), at temperatures ranging from 298 to 573 K. The JBS sensor exhibited a higher ideality factor and barrier height owing to the p–n junction in JBS devices. The developed sensor showed good repeatability, maintaining a stable output over several cycles of measurements on different days. It is worth noting that the ideality factor and barrier height influenced the forward biased voltage, leading to a higher sensitivity for the JBS device compared to the SBD device. This allows the JBS device to be suitably integrated with SiC power management and control circuitry to create a sensing module capable of working at high temperatures.