Course ObjectiveAfter you finished this course, you will be able to use existing
software for the analysis of natural language and to combine software to
automatically mine information from large amounts of text. You have the
knowledge to interpret the results and you can adjust the software
Course ContentIn this course, you learn what it takes to build your own reading
machine. A reading machine is a complex piece of software that applies a
large variety of linguistic analyses to a text, each producing a
different type of output. You will learn to segment and tokenise text
and to detect the part-of-speech of words, how to split compounds,
detect entities, events and participants in text, detect emotions and
opinions, interprete temporal expressions, etc. Various aspects of
designing such systems are discussed: how to combine the output of
different modules, how to handle ambiguity, dependencies, error
propagation from one module to the next, how to design top-down,
bottom-up and hybrid approaches and how to involve background knowledge.
Finally, the result of the processing needs to be combined in output
data that the computer can understand and use for reasoning.
Teaching Methodsinteractive lectures, assignments and practical classes.
Method of AssessmentThe course is graded by the assignments and the results of the practical
classes (50%) and a final assignment (50%). Both components must be
graded at least 5.5.
Entry RequirementsLinguistic Research, Programming in Python, Deep Learning for NLP,
Language as Data
LiteratureTo be announced
Target AudienceMaster students in (specialisation Text Mining) and master students with
a background in programming and NLP
|Language of Tuition||English|
|Faculty||Faculty of Humanities|
|Course Coordinator||prof. dr. P.T.J.M. Vossen|
|Examiner||prof. dr. P.T.J.M. Vossen|
prof. dr. P.T.J.M. Vossen
You need to register for this course yourself
Last-minute registration is available for this course.
This course is also available as: