Natural SQL: Making SQL Easier to Infer from Natural Language Specifications

Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts in the text descriptions; (2) removing the need of nested subqueries and set operators; and (3) making the schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benchmark that contains complex and nested SQL queries, we demonstrate that NatSQL outperforms other IRs, and significantly improves the performance of several previous SOTA models. Furthermore, for existing models that do not support executable SQL generation, NatSQL easily enables them to generate executable SQL queries, and achieves the new state-of-the-art execution accuracy.

Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer

Strong and affordable in-domain data is a desirable asset when transferring trained semantic parsers to novel domains. As previous methods for semi-automatically constructing such data cannot handle the complexity of realistic SQL queries, we propose to construct SQL queries via context-dependent sampling, and introduce the concept of topic. Along with our SQL query construction method, we propose a novel pipeline of semi-automatic Text-to-SQL dataset construction that covers the broad space of SQL queries. We show that the created dataset is comparable with expert annotation along multiple dimensions, and is capable of improving domain transfer performance for SOTA semantic parsers.

ضمان جودة التعليم في القطاعات التعليمية الخاصة نظام لتقييم المدرسين في الجامعات (تطبيق على جامعة القلمون الخاصة)

In this thesis, we review the problems of instructors’ assessment and propose some solutions in the context of an assistant system for the evaluation of instructors in higher education institutions, and implement this system at the University of kalamoon as a practical case with real data to verify results. This research aims to prove the possibility of a flexible system in selecting instructors’ evaluation criterias in accordance with the chosen institution, and in the objectivity and impartiality of the assessment of instructors and the accuracy and the consistency of decision makers' opinions.

Using Data Mining Techniques to Analyze Students’ Performance

The objective of this paper is presenting an educational data mining case study, by applying data mining techniques.