Browsing by Subject "NLIDB"

Now showing 1 - 3 of 3

Open Access
Effective and explainable mechanisms for natural language interface in databases
(2021-09) Karakayalı, Akifhan
Structured Query Language (SQL) is a commonly used tool to extract and present structured data stored in Relational Database Management Systems (RDBMSs), yet inherited complexities of SQL create barriers for naive users who are capable of expressing queries as natural language queries (NLQs). In order to tackle this barrier we propose two di erent solutions; a Natural Language Interface to Database (NLIDB) pipeline with an explainable AI interface and a semantic search strategy. The rst solution introduces a NLIDB pipeline that uses SQL translation algorithms along with a keyword mapper to generate SQL queries for given NLQs. Proposed pipeline is presented to the user with an explainable AI interface so that the user can reason over the constructed query. We compared our approach with two state-of-art systems; NALIR+ and Pipeline+. Our approach surpass NALIR+ in imdb, scholar and yelp datasets achieving 88.9%, 100% and 60.0% translation accuracy for single table SELECT-JOIN queries and 68.6%, 87.0% and 83.6% translation accuracy for multiple table SELECT-JOIN queries, respectively. Our approach outperforms Pipeline+ in imdb and scholar datasets but Pipeline+ is slightly better in yelp dataset. The second solution proposes a semantic search approach that uses Information Retrieval based methods to retrieve related table rows for a given NLQ. The proposed approach uses the graph representation of the database where each row and value is represented with a node and edges represent the relation between them. Query and database rows are converted to vector representations using this graph representation and Graph Convolutional Networks (GCNs). A similarity calculation is performed using these vector representations and database rows are ranked according to their relevance to the query. Cosine distance metric is employed for similarity calculation. We tested our approach with college schema from Spider dataset collection and achieved a 42.8% top-5 accuracy.
Open Access
Towards deeply intelligent interfaces in relational databases
(2021-08) Usta, Arif
Relational databases is one of the most popular and broadly utilized infrastruc-tures to store data in a structured fashion. In order to retrieve data, users have to phrase their information need in Structured Query Language (SQL). SQL is a powerfully expressive and ﬂexible language, yet one has to know the schema underlying the database on which the query is issued and to be familiar with SQL syntax, which is not trivial for casual users. To this end, we propose two diﬀerent strategies to provide more intelligent user interfaces to relational databases by utilizing deep learning techniques. As the ﬁrst study, we propose a solution for keyword mapping in Natural Language Interfaces to Databases (NLIDB), which aims to translate Natural Language Queries (NLQs) to SQL. We deﬁne the key-word mapping problem as a sequence tagging problem, and propose a novel deep learning based supervised approach that utilizes part-of-speech (POS) tags of NLQs. Our proposed approach, called DBTagger (DataBase Tagger), is an end-to-end and schema independent solution. Query recommendation paradigm, a well-known strategy broadly utilized in Web search engines, is helpful to suggest queries of expert users to the casual users to help them with their information need. As the second study, we propose Conquer, a CONtextual QUEry Recom-mendation algorithm on relational databases exploiting deep learning. First, we train local embeddings of a database using Graph Convolutional Networks to ex-tract distributed representations of the tuples in latent space. We represent SQL queries with a semantic vector by averaging the embeddings of the tuples returned as a result of the query. We employ cosine similarity over the ﬁnal representations of the queries to generate recommendations, as a Witness-Based approach. Our results show that in classiﬁcation accuracy of database rows as an indicator for embedding quality, Conquer outperforms state-of-the-art techniques.
Open Access
xDBTagger: explainable natural language interface to databases using keyword mappings and schema graph
(Springer, 2023-08-23) Usta, A.; Karakayalı, A.; Ulusoy, Özgür
Recently, numerous studies have been proposed to attack the natural language interfaces to data-bases (NLIDB) problem by researchers either as a conventional pipeline-based or an end-to-end deep-learning-based solution. Although each approach has its own advantages and drawbacks, regardless of the approach preferred, both approaches exhibit black-box nature, which makes it difficult for potential users to comprehend the rationale behind the decisions made by the intelligent system to produce the translated SQL. Given that NLIDB targets users with little to no technical background, having interpretable and explainable solutions becomes crucial, which has been overlooked in the recent studies. To this end, we propose xDBTagger, an explainable hybrid translation pipeline that explains the decisions made along the way to the user both textually and visually. We also evaluate xDBTagger quantitatively in three real-world relational databases. The evaluation results indicate that in addition to being lightweight, fast, and fully explainable, xDBTagger is also competitive in terms of translation accuracy compared to both pipeline-based and end-to-end deep learning approaches.