Pinpoint

Temporal and Spatial Awareness Engine

LCC's Pinpoint provides temporal and spatial awareness for absolute or relative mentions of times, dates, and locations.

Introduction

LCC's Pinpoint temporal and spatial normalization system unlocks value from raw texts by automatically converting temporal and spatial expressions into formats that can be easily visualized.

While state-of-the-art named entity recognition systems (like LCC's CiceroLite) can identify names of locations, dates, and times with near-human accuracy, natural language texts are full of underspecified or inexact temporal or spatial expressions that must be resolved before they can be utilized by an information consumer.

Precise Location Identification

Pinpoint provides the information needed to precisely locate mentions of spatial expression in texts.

  • Find the exact latitude and longitude for nearly 8 million locations worldwide.
  • Resolve non-exact place names to their physical locations. (e.g. the Sunni Triangle, the Tri-State Area, the Sun Belt).
  • Disambiguate ambiguous place names (e.g. Springfield, Red River) based on contextual and real-world cues.
  • Fully specify partial mentions of place names in texts (e.g. Austin: Austin, TX).
  • Search for place names corresponding to relative spatial expressions (e.g. north of Baghdad).
Reliable Temporal Resolution

Pinpoint accurately resolves mentions of dates and times in texts to their ISO 8601 equivalents.

  • Automatically extract the publication/creation date for documents.
  • Identify the unique date associated with each absolute (e.g. June 13th) or nonspecific time expression (e.g. today, Monday, last week) found in a text.
  • Associate relative time expressions (e.g. late in the evening, around midnight) with probable date/time ranges.
  • Associate recurring date or time expressions to sets of exact temporal expressions (e.g. the first Monday of each month, every 5 minutes from 10:00 to 1:00).

How it Works

Pinpoint leverages an award-winning combination of machine-learning and heuristic-based approaches to associate instances of dates, times, and locations in texts with a normalized expression that can be exported to a wide range of visualization or natural language processing applications.

Whether used in conjunction with entity annotations provided by LCC's CiceroLite - or other commerically-available entity recognition solutions - Pinpoint provides the accurate and reliable temporal and spatial expression resolution information consumers need to take full advantage of text annotation tools.

Designed for easy deployment, Pinpoint is released with a pure Java API that allows for straightforward integration with other information processing systems. A wide range of file formats are supported, including HTML, SGML, XML, PDF, and Microsoft Word documents.

Live Demo

Unfortunately, we don't have a demo of this application available on the web yet. Visit LCC Labs to browse our current selection of demos.

Integrating other applications with OpenCicero

To integrate PinPoint into your natural language processing environment, you can use OpenCicero.

Hardware / Software Requirements

LCC's PinPoint was designed to run on standard hardware. Have questions about whether it'll run in your environment? E-mail us at support@languagecomputer.com.

  • Minimum Specifications: single-core 2.0 GHz processor , 1 GB of available RAM at run-time.
  • Recommended Specifications: multi-core 2.0 GHz (or better) processor, 2 GB of available RAM.
  • Supported Operating Systems (Desktop Applications): Microsoft Windows (95, 98, XP, Vista, 7), OS X, Linux (RedHat, CentOS, Ubuntu, etc.), Solaris.
  • Supported Web Service Protocols: SOAP, REST.

Supported Languages

PinPoint is only currently available for English. Interested in other languages? Contact us at at support@languagecomputer.com for an estimate.

For More Information

For more information about PinPoint, call our product support team at (972) 231-0052, or e-mail us at support@languagecomputer.com.