Helping you unlock insights through integrated text processing

tokenmill logo 

Accelerated Text

Screenshot of Accelerated Text

About Accelerated Text

Accelerated Text is a “data to text” natural language generation tool which allows you to define data descriptions and then generates multiple versions of those descriptions varying in wording and structure. It can work with much of your data:

  • Business metrics
  • Customer interaction data
  • Product attributes
  • Financial metrics

You can generate text for your business reports, your e-commerce platform, or your customer support system.

Philosophy

Natural language generation is a broad domain with applications in chat-bots, story generation, and data description to name a few. Accelerated Text focuses on applying NLG technology to solve your “data to text” needs.

Data descriptions require precision. For example, a text describing weather conditions can not invent things beyond what it was provided: Temperature: -1C, Humidity: 40%, Wind: 10km/h. A generated text can only state those facts. The expression of an individual fact - temperature - could vary. It could result in a "it is cold", or "it is just below freezing", or "-1C" but this fact will be stated because it is in the data. A "data to text" system is also not one to elaborate on a story about the serenity of the freezing lake - again, it was not in the supplied data.

Accelerated Text follows the principle of this strict adherence to the data-bound text generation. Via its user interface it provides instruments to define how the data should be translated into descriptive text. This description - a document plan - is executed by its natural language generation engine to produce texts that vary in structure and wording but are always and only about the data provided.

github icon Accelerated Text on GitHub

tokenmill logo 

Areas of Expertise

Targeted Crawling

Example: crawl 10,000,000 web pages per day and make them available for enterprise search.

Website Parsing

Example: given a list of websites of investment funds, determine the geographic make up of their exposure.

Search and Discovery

Example: index 500,000 quarterly reports, then determine what is important to rank in the top 10 for each query of interest.

Media Parsing

Example: identifying market reactions to fluctuations of commodity prices as manifested in popular media.

Corporate Document Parsing

Example: Retrieve auditor details from a repository of quarterly company reports.

Natural Language Generation

Example: automatically generate monthly employee performance reports for different stakeholders.

A Few of Our Past Projects

client logo

Venture Radar (UK)

NLP pipeline with crawler and venture capital funding event detection.

client logo

Weborama (FR)

NLP library used as part of Weborama's media monitoring package.

client logo

SaasMAX (US)

Custom company web page crawl to extract information about business activities.

client logo

ROI: Recruit (SE)

NLP pipeline with crawler, job advertisement identification and contact person recognition.

client logo

Orbit Financial Technology (UK)

NLP pipeline with crawler. Event detection related to financial instruments. Timeseries database population.

client logo

Kaunas University of Technology (LT)

Crawler, named entity recognition, text classification, clustering, deduplication, text similarity estimation and sentiment analysis.

client logo

Social Artisan (UK)

NLP pipeline with web and social media crawler, named entity recognition, sentiment analysis and article classification.

client logo

Agency for Science, Innovation and Technology (LT)

Open source word stemmer and page function identification algorithm. Research into customer care messages classification.

tokenmill logo 

Our Team

photo

Zygimantas Medelis
CEO
github icon linkedin icon

photo

Sarunas Navickas
Data Engineer
github icon linkedin icon

photo

Rokas Ramanauskas
Software Engineer
github icon linkedin icon

tokenmill logo 

Contact Us