Text Processing

Text processing in CorText is divided in two families wether you are dealing with raw textual content or categorial data.

Lexical Extraction  and Term Indexer scripts are deemed to be used with textual content (made of paragraphs or full sentence)

List Builder and List Indexer are rather dedicated to working with data which are single words or expressions like a name, an institution, or any category-like information.

In both cases the Csv Viewer and Editor is instrumental to manage extracted lists.

Text processing documentation

Terms Extraction

Terms extraction automatically identifies terms pertaining to a given corpus. In fact, Natural Language Processing (see supported languages below) tools that we use allow us to identify not only simple terms but also multi-terms (called n-grams). How to use Terms Extraction Textual fields definition Select the textual fields you wish to analyze and index: If ...

corpus terms indexer

This script works hand in hand with the lexical extraction. Actually, by default, it is even automatically launched every time a lexical extraction is executed. Its basic objective is, given a series of textual fields (provided by the user), to index every term found in a given term list csv file (specified by the user). ...

list builder

List builder helps you manage categorial entities. Not only does it provide lists of most frequent textual entities for a given field but it also creates a list of potentially duplicate entries when raw data are noisy (potentially useful for cited references, names, cited journals, addresses etc.)   How to use the script Field Select ...

corpus list indexer

This script is naturally connected to list builder script. It provides users with full control other a set of items that may later get mapped or analyzed. Technically, one or several new field(s) will be created  using a key defined by user along previously uploaded TSV (csv) files. How to use the script Field Select ...

Named Entity Recognizer

The script is based on Named Entity Detection  capacities offered by spacy. It allows to identify and index persons, places, organizations, etc. At the moment it can handle 5 different languages. In English, one can select among 10 kinds of entities (date: DATE, products: PRODUCT, people: PERSON, geological entities: GPE, etc.). 4 kinds of entities are automatically ...

Sentiment Analysis

Sentiment analysis is “the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer’s attitude towards a particular topic, product, etc. is positive, negative, or neutral.” Oxford Dictionary Methods to perform sentiment analysis CorText Manager offers two different ways to perform sentiment analysis. Textblob ...

csv editor

A csv and tsv file viewer and editor is generated every time CorText produces a csv (mainly for results) or a tsv (for terms, dictionaries, resources…) file that may require further editing from users, particularly following a term extraction or list building scripts. To access to the interface, simply click on the .csv or .tsv ...

Latest questions in the Q&A forum on text processing

Filter:AllOpenResolvedClosedUnanswered
Answeredmatias.milia asked 2 months ago • 
112 views2 answers1 votes
AnsweredAnne-Lise Dauphiné-Morer asked 4 months ago • 
119 views3 answers0 votes
AnsweredMatthieu P asked 5 months ago • 
76 views1 answers0 votes
AnsweredDéborah Abhervé asked 6 months ago • 
128 views4 answers0 votes
AnsweredGabrielle Bouleau asked 7 months ago • 
109 views1 answers0 votes
AnsweredGabrielle Bouleau asked 6 months ago • 
78 views1 answers0 votes
AnsweredYuri Saldarriaga asked 9 months ago • 
183 views2 answers0 votes