LiRI Wiki

This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong.
====== Natural Language Processing ======

If any of the following applies to you, you are in the right place:

  * As a researcher, do you want to base your empirical findings on linguistic data such as text collections or voice recordings?
  * Does your team need help in collecting, managing, processing, or visualising linguistic data?
  * Do you want to automate tedious manual tasks?
  * Do you intend to make your documents machine-readable?
  * Do you want to detect historical trends, political leanings, and personal stance in natural language data?
  * Do you have an interesting application in mind which is built on text, audio recordings or eye-tracking data?
  * Do you want to use semantic analysis methods like collocations, word embeddings and Neural Networks?
  * Do you want to get started implementing language technology solutions yourself?
  * Do you have historical documents that you are looking to digitize?

If you need help with the technological side of things, we are here for you!

The [[start]] group consists of experts who support your text and voice technology needs.

  * Text Analytics & Data Mining
  * Content Analysis
  * Information Retrieval & Extraction
  * Part-of-speech tagging, syntactic parsing, semantic tagging
  * Sentiment Detection
  * Creation and adaption of language models 
  * Data Classification
  * Machine Learning (including Neural Networks & Deep Learning)
  * Machine Translation
  * Statistical Data Processing
  * Audio signal processing (e.g. for human speech or animal vocalizations)
  * Speech Recognition and Synthesis
  * Data conversion

We offer consulting, coaching, and support in the following scenarios (among others):

  * Digitization of printed texts and manuscripts (including OCR)
  * Efficient information extraction and analysis of large text collections
  * Enrichment of texts with named entities, sentiment analysis, topic modeling, and classification, including multilingual and historical documents
  * Advice on tools, software, and best practices
  * Help with project applications and common projects


===== Teasers from our Research =====

==== Coaching and Teaching ====

Example from a Worskshop, teaching Content Analysis with R

{{coaching.png?600|}}
----

==== Semantic Analysis ====

Example of a Result: Conceptual Map of Associations to Wine, Cider and Beer

{{cider_wine_beer.png?600|}}
----

==== Stylistics ====

Characterisation of the Language of Donald Trump

{{trump1.png?400|}}
{{trump2.png?400|}}

https://www.blick.ch/news/linguistik-trumps-sprache-einfach-sprunghaft-und-emotional-id16163332.html
----

==== Examples of our work ====

Speech-to-text backend for virtual telephone switchboard

{{vr_telefonzentrale.png?600|}}

[[https://www.ds.uzh.ch/de/projekte/vr.html]]