AI News, Pragmatic Approach to Structured Data Querying via Natural Language Interface

Pragmatic Approach to Structured Data Querying via Natural Language Interface

Introducing the research paper that describes a practical approach to building natural language interfaces for structured data querying.

Today’s information retrieval technologies utilized by companies claim to democratize data but the reality is that these technologies are very complex and require understanding of query languages, such as SQL, strong analytical skills, extensive training, and knowledge of data structure to formulate a valid query.

To reduce some burden on already overstretched data teams, many organizations are looking for self-service tools that allow non-developers to query databases using natural language without needing a data analyst for every report.

Now we’re pleased to share the research paper “A pragmatic approach to structured data querying via natural language interface”, where we describe our algorithm in detail and discuss a number of factors that can dramatically affect the system architecture and the set of algorithms used to translate NL queries into a structured query representation.

A Pragmatic Approach to Structured Data Querying via Natural Language Interface

As the use of technology increases and data analysis becomes integral in many businesses, the ability to quickly access and interpret data has become more important than ever.

Today’s information retrieval technologies utilized by companies claim to democratize data but the reality is that these technologies are very complex and require understanding of query languages, such as SQL, strong analytical skills, extensive training, and knowledge of data structure to formulate a valid query.

Besides high accuracy, our approach provides additional benefits over machine learning methods: In this post, we want to share our research paper 'A pragmatic approach to structured data querying via natural language interface', where we describe our algorithm in detail and discuss a number of factors that can dramatically affect the system architecture and the set of algorithms used to translate NL queries into a structured query representation.

Tableau acquires ClearGraph, a startup that lets you analyze your data using natural language

Business intelligence and analytics firm Tableau today announced that it has acquired ClearGraph, a service that lets you query and visualize large amounts of business date through natural language queries (think “this week’s transactions over $500”).

Tableau expects to integrate this technology with its own products as it looks to make it easier for its users to use similar queries to visualize their data.

Recent advances in natural language processing and machine learning now allow services like ClearGraph to understand more about the underlying database and then take these sentences and essentially translate them into database queries.

While the company doesn’t disclose who its customers are (which is not unusual in the enterprise space), Ajenstat tells me that they include financial institutions, retailers and major internet companies.

As Ajenstat noted, every company today struggles to make its data accessible to more of its employees, so it doesn’t come as a surprise that ClearGraph’s customers span a wide range of verticals.

Tableau Acquires Natural Language Query Startup ClearGraph

SEATTLE, WA – August 9, 2017 – Tableau Software (NYSE: DATA) today announced it has acquired ClearGraph, a cutting edge Palo Alto startup that enables smart data discovery and data analysis through natural language query technology.

“Natural language queries will make it easier for more people to interact with Tableau, whether you’re an executive who needs an answer quickly, or on a mobile phone and want an answer from your data on the move.

We’re excited about this acquisition as the ClearGraph team shares our mission and is aligned with our innovation perspectives on conversational analytics.” ClearGraph makes it easy to analyze data using natural language.

For example, people could ask questions such as, “Total sales by customers who purchased staples in New York,” then filter to, “orders in the last 30 days,” then group by, “project owner’s department.” “We founded ClearGraph because we saw a need to bridge the gap between humans and computers through natural language, especially when it comes to exploring data,” said Andrew Vigneault, CEO of ClearGraph.

press release contains forward-looking statements that involve risks and uncertainties, including statements regarding Tableau’s proposed product offerings, future product capabilities and investments in product development.

There are a significant number of factors that could cause actual results to differ materially from statements made in this press release, including challenges integrating ClearGraph technology and personnel;

How is natural language processing applied in Business?

We have always heard “This call may be recorded for quality and training purposes” when we call the company’s call centres for required services.

The insights gained from this information have driven businesses into a new domain of customer understanding, but limiting the analytics to this type of highly structured format excludes the majority of the data that’s being created at present.

The challenge here with Natural Language Processing is that computers normally requires humans to talk in the programming language, which has to be explicit and highly structured, although natural language is anything but explicit.

Although companies always consider sentiments (positive or negative) as the most significant value of the opinions users express through social media, the reality is that emotions provide a lot of information that addresses customer’s choices and it even determines their decisions.

For example: If customer complaints through message or email about their issues with service or product, a Natural Language Processing system would recognize the emotions, analyze the text and mark it for a quick automatic reply accordingly.

Instead of trying to understand concepts based on normal human language usage patterns, the company’s platform depends on a custom knowledge graph that is created for each application and perform a much better job identifying concepts that are relevant in the customer domain.

With the arrival of advanced statistical algorithms, programs are now capable of using statistical inference to understand the human conversation by calculating the probability of certain results.

Sand Dance, Natural language querying and Cortana integration

In this video, I'd like to showcase the capabilities of the "Sand Dance" Custom visuals using PowerBI desktop by analyzing the Sales data of an E-Commerce ...

RDBMS to Graphs

William Lyon, Developer Relations Engineer, Neo4j:Relational databases were conceived to digitize paper forms and automate well-structured business ...

Demo: DataRPM Natural Language Analytics

In this slidecast, Sundeep Sanghavi from DataRPM demonstrates the company's innovative Natural Language Analytics software. "DataRPM is a revolutionary ...

What Is Your Data Science Super Power? Tips and Tricks to Successful Data Science

How do businesses and data scientists turn raw data into intelligent action? Why do some companies drown in volumes of data, while others thrive on turning it ...

Database Lesson #3 of 8 - The Structured Query Language (SQL)

Dr. Soper gives a lecture on using the structured query language (SQL) to work with databases. Topics include CREATE, ALTER, and DROP statements, ...

Behind the Cloud Episode 4: The Path to Becoming a Data-Driven Organization

Pete Schlampp, vice president of Workday Analytics, talks with host David Clarke about why making sense of business data is no longer the strict purview of the ...

Put your time series data to work for your business - BRK2253

Use your time series IoT data to better understand machine, building, and device time series data. Using Azure Time Series Insights, we'll show you how to ...

Building A Petabyte Scale Warehouse in BigQuery (Cloud Next '18)

BigQuery was built on top of Dremel, Google's internal analytics workhorse. It was only natural for BigQuery to support use cases of all sizes, all the way up to ...

From RDBMS to Graphs

Ryan Boyd, Developer Relations,Neo Technology:A graph database like Neo4j naturally stores, manages, analyzes, and uses data within the context of ...

Data Refinery in Watson Studio

If you are like most data scientists, you are probably spending a lot of time to cleanse, shape and prepare your data before you can actually start with the more ...