logo


XLPAT-Corpus: Technical thesaurus for IP professionals, Attorneys, Researchers

XLPAT introduces a technical corpus containing more than 3 billion words with over 100 GB of processed data and developed on a Machine learning model trained with 200+ machine hours.

IP professionals constantly face a challenge of finding related keywords/semantics for a particular technical word. Majority of research documents published worldwide are written using different terminologies based on the origin country and the subjectivity of the writer. This presents multiple term variations used globally for a single technical word. The swiftly updating technology also introduces new jargon of words which was previously unknown worldwide.

The job of retrieving documents for a particular technology using a search engine requires the researcher to use all possible semantic variations of the word to ascertain an exhaustive coverage. Additionally, for drafting a patent or a thesis effectively, a writer has to use different terminologies for which currently he has to rely on his prior technical experience.

Online dictionaries as of now, do not cater to the technical terms and are mostly based on routine english words. This makes the job of locating semantics of technical words a time consuming and an arduous task. XLPAT-CORPUS solves this global problem and is developed on a data-set of scientific documents with concurrently training the machine learning model with inputs from more than 200 researchers from different technological backgrounds of electronics, mechanical, computer sciences and more.

USE CASES
Case Study 1 : Identifying the broader parent words and application areas of a particular term

A word such as “Magnetorheological” when inputted into the Corpus system retieves below wordlist :

  • Magnetorheological fluid
  • Electrorheological fluid
  • Smart fluid
  • Electrorheological liquid
  • Rheological fluid
  • Magnetorheological liquid
  • Field responsive fluid
  • Controllable fluid
  • Magnetorheological fluid damper
  • Electroviscous liquid
  • Electroviscous fluid
  • Controllable damper

The user will develop an understanding that a magnetorhelogical fluid is a category of “Smart fluid” and there would be documents in which the broader parent word “Smart fluid” will be written which encompasses magnetorhelogical fluid inferentially.

Additionally, the word “Controllable damper” displayed in the wordlist provides an indication to the user of possible application areas of magnetorheological fluid in such devices.

Case Study 2 : Identifying semantic variations while drafting a patent/research paper

A second example is a term “Prosthesis”. While writing a patent draft or a research paper a drafter wants a list of all variations which can be used for the term “Prosthesis”. Using different term variations is a technique frequently used by drafters to write claims in a patent which differentiates it literally from Prior Art. Semantic variations also enhances the overall writing quality of the draft or research paper.

The Corpus system retrieves below wordlist for “Prosthesis” :

  • Implant
  • Transplant
  • Stent
  • Graft
  • Catheter
  • Dilator
  • Introducer

Such variations can be used by the drafter.

The use cases of an enriched technical corpus are numerous and XLPAT-Corpus can be used to fit your requirements.

It is also very convenient for non-english IP professionals for finding correct english terminology.





Did you mean {{synonym.set_unset[1]}}?


scientist   Scientist Opinion
Proficiency: Excellent
Engineer   Engineer Opinion
Proficiency: Good
Acadamician   Student Opinion
Proficiency: Average

No Corpus Results!

  •    {{value}}

  • No Corpus Results!

  •    {{value}}


  • Show More

    Contribute to tool

    Export List






    Was it Useful?