PACTE - Collaborative electronic text annotation platform


PACTE is a collaborative annotation web platform for text content that integrates an array of practical tools for research groups. It offers two annotation modes, manual and automatic, and is available in English and French to facilitate research and collaboration. 

Manual annotation is carried out by means of an interface optimized to allow rapid entry of the data enriching a text. The automatic mode is composed of all the specialized and configurable annotation services (named entities, disambiguated terminology, etc.).

Users can interact with PACTE using the online user interface or the application programming interface API (REST API) to access all their data and facilitate algorithm development based on rich resources. 

With this collaborative web platform, analyses and annotations can be shared between users, thereby facilitating cooperation and opening the door to large-scale multi-partner studies. Using PACTE generates considerable gains in productivity by significantly reducing annotation time while facilitating the analysis of annotated data.
 

Services

 
Morphosyntactic analysis

Parse each word’s morphosyntactic function, grammatical gender, number, lemma, etc.

 
 
Document profile

Identify a document’s relevant domains through a specialized terminology lexicon.


 
Terminology disambiguation

Annotate texts using lexicon's terms that are directly related to a given field.


 
Recognize a named entity

Isolate expressions designating named entities: people, places, organizations, geopolitical entities...


 
Active learning (in development)

Train a prediction model with minimal annotation effort thanks to new algorithms selecting the examples, thus providing the best information for the model. 

 

Main features

  • Create, import and access your corpora. 
  • Import text documents in various formats (doc, docx, pdf, html, etc.).
  • Create and modify your annotations.
  • Consult an existing lexicon or built your own!
  • Assign annotation tasks to team members.
  • Manage your contacts and share your corpora and annotation schemas.
  • Launch one of our linguistic, lexical or semantic annotation tools.
  • Work in English or in French, depending on team members' preferences.
  • Structure the information you need to enrich your documents.
  • Find the relevant documents according to annotation type.
  • No service matches your needs? Train your own, customized annotator! (in development)

 

Discover and try PACTE here!

 

 

Read the white paper

Scientific publications

Ménard, P. A. and Barrière, C. "PACTE: a collaborative platform for textual annotation" in Proc of the 12th International Conference on Computational Semantics (IWCS 2017). Montpellier, France, September 19 to 22, 2017 
 
Bernier-Colborne, G., Barrière, C. and Ménard, P. A. "Fine-grained domain classification of text using TERMIUM Plus" in Proc of the 12th International Conference on Computational Semantics (IWCS 2017). Montpellier (France), September 19 to 22, 2017 

 

Reasearch platforms

Created as part of CANARIE-funded projects, the research platforms developed by CRIM are available on the CANARIE's Research Software Portal, which gives access to a range of platforms and software services to researchers in order to accelerate discovery. 

 Discover VESTA: a collaborative multimedia content annotation platform

 

Teams

Recent news

  • COVID-19 : Suivi de la situation
    25/03/2020

    Notre équipe maintient ses opérations à distance et est toujours là pour vous servir.

    +

Upcoming event

  • Assemblée générale des membres du CRIM - 18 juin 2020
    18 June 2020 0:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    Les membres du CRIM sont convoqués à l'Assemblée générale annuelle qui se tiendra le 18 juin 2020. Ne manquez pas cette importante réunion et l'occasion de vous tenir au fait de plusieurs dossiers qui vous concernent.
    +
  • Prompt RT @Prompt_Innov: [ WEXPERT ?La Ville intelligente Nos intervenants : Philippe Beaudoin, co-fondateur d’ @element_ai Stéphane Barbier, di…
  • CEIM RT @CEIM_Qc: Bonne nouvelle! Le gala de l' @ADRIQ_RCTi aura bien lieu, que ce soit en présentiel ou en virtuel! Ne passez pas à côté de cet…

Recent Publications

  • An ensemble Based Approach for Generalized Detection of Spoofing Attacks to Automatic Speaker Recognizers

    +
  • Generalized End-to-End Detection of Spoofing Attacks to Automatic Speaker Recognizers

    +