TEXT·A·GRAM

Text analysis from the point of view of text grammars


There are some news (September 7th, 2026): Some months before we mentioned that there was a new semantic tagger that would replace the one implemented here in Text·a·gram. Well, it turns out that we have yet another one, now called ``Wikacho'' (with a k). This new device combines the previous two and is therefore based on both Wiktionary and Wikipedia. We will soon integrate this tagger here, but in the meantime, but if you want to check it out visit its own website: http://www.tecling.com/wikacho. Right now it only works with texts in Spanish, though. The English version is still in preparation.

The referent analysis (semantic tagging) can also be made in English.
The analysis of discourse markers can also be made in English, French, Catalan and German, but developments in these languages is still very limited.

Select the type of analysis:
El barrido de referentes estará desactivado mientras terminamos de reemplazar este componente por la nueva versión, llamada Wikacho, que por su parte está ya disponible en su propio sitio web: http://www.tecling.com/wikacho
El resto de las funciones, sin embargo, sigue disponible:
Documentation:
Tagging 1: referents
Tagging 2: discourse markers
Tagging 3: deixis
Tagging 4: modalization


(back)

===================================

This is another project by Tecling.com
Publications
About the semantic tagger

The version of the semantic tagger currently implemented in Text·a·gram is the first one, called Tatatag, from 2025, which is the tagger based on Wiktionary. This version is described on the following paper:

• Nazar, R. (2026). Semantic Typing for Corpus Pattern Analysis. International Journal of Lexicography, vol. 39, 2026, ecag012.


Later (2026), we developed Wicacho, a new version of the tagger that uses Wikipedia (http://www.tecling.com/wicacho). This sencond version is described in another paper:

• Nazar, R.; Renau, I. (2026). Wikipedia used as a semantic tagger: some preliminary results in Spanish. Procesamiento del Lenguaje Natural, n. 76, p. 279-292.

Now (September 7, 2026) we have a third version (Wikacho: http://www.tecling.es/wikacho) that combines both approaches integrating Wiktionary and Wikipedia. No paper has been published about it yet, but we are preparing some documentation on the website.


Publications about the rest of the functions in Text·a·gram
• Nazar, R. (2024). Statistical modeling of discourse genres: the case of the opinion column in Spanish. SN Computer Science 5(959):1-11.
• Nazar, R.; Renau, I.; Robledo, H. (2024). Dismark and Text·a·Gram: Automatic identification and categorization of discourse markers in texts. In: Cecilia-Mihaela Popescu & Oana-Adriana Dut,ă (eds.), Discourse Markers in Romance Languages. Crosslinguistic Approaches in Romance and Beyond. Berlin: Peter Lang.

This is open source-software


This is the code of the module of the semantic tagging (Tatatag):
https://tecling.es/textagram/tatatag-source.zip
But remember that this version is already deprecated and will soon be replaced by the new one (Wikacho: http://www.tecling.es/wikacho)

Evaluation dataset


This is the evaluation of the old version (Tatatag). It will also be replaced soon. The data used for evaluation consist of Wikipedia pages, 179 in Spanish and 241 in English.
https://tecling.es/textagram/evaluationData.zip
The data here is presented in html format. It includes pages about 19th Century British politicians and Argentine generals of the same period. Files are numbered and each one is associated with an 'evaluation' file, where results are evaluated. At first, we did the evaluation ourselves, but then we opted to use Gemini API to evaluate results. The evaluation is not pefect but is pretty close to human. We are in the process of evaluating the evaluation. More on this soon.
You can also browse the evaluation data here.

The modules for the analysis of discourse markers, deixis and modalization are here:
https://tecling.es/textagram/text·a·gram.zip
This code allows for the local execution of the program, which allows to analyze many documents at the same time. The code is composed of a Perl script and some csv tables. It uses R for the graphs (the online version, instead, uses the GD Graph library). You will have to adjust the paths in the script to match those of your system, especially if you are a Windows user.

Concept and development: Rogelio Nazar

Collaborators: Javier Obreque, Diego Sánchez, Hernán Robledo, Paolo Caballería, Nicolás Acosta, Scarlette Gatica, Andrea Alcaíno, Ignacio Lobos and Irene Renau.

Documentation: Andrea Alcaíno & Rogelio Nazar