Natural Language Interfaces to Data
Abdul Quamar, Vasilis Efthymiou, Chuan Lei, Fatma \"Ozcan

TL;DR
This paper reviews recent advances in natural language interfaces to data, covering rule-based, deep learning, and hybrid approaches, and discusses challenges, conversational interfaces, and evaluation benchmarks for NLQ systems.
Contribution
It provides a comprehensive survey of technologies, methods, and benchmarks in natural language querying to data, highlighting recent progress and future directions.
Findings
Deep learning models improve NLQ interpretation accuracy.
Hybrid approaches combine rule-based and DL techniques effectively.
Conversational interfaces enable multi-turn data querying.
Abstract
Recent advances in NLU and NLP have resulted in renewed interest in natural language interfaces to data, which provide an easy mechanism for non-technical users to access and query the data. While early systems evolved from keyword search and focused on simple factual queries, the complexity of both the input sentences as well as the generated SQL queries has evolved over time. More recently, there has also been a lot of focus on using conversational interfaces for data analytics, empowering a line of non-technical users with quick insights into the data. There are three main challenges in natural language querying (NLQ): (1) identifying the entities involved in the user utterance, (2) connecting the different entities in a meaningful way over the underlying data source to interpret user intents, and (3) generating a structured query in the form of SQL or SPARQL. There are two main…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
